Imad Bou-Hamad, Denis Larocque, Hatem Ben-Ameur

Source: Statist. Surv., Volume 5, 44--71.

Abstract:
This paper presents a non–technical account of the developments in tree–based methods for the analysis of survival data with censoring. This review describes the initial developments, which mainly extended the existing basic tree methodologies to censored data as well as to more recent work. We also cover more complex models, more specialized methods, and more specific problems such as multivariate data, the use of time–varying covariates, discrete–scale survival data, and ensemble methods applied to survival trees. A data example is used to illustrate some methods that are implemented in R.

Gregory J. Matthews, Ofer Harel

Source: Statist. Surv., Volume 5, 1--29.

Abstract:
There is an ever increasing demand from researchers for access to useful microdata files. However, there are also growing concerns regarding the privacy of the individuals contained in the microdata. Ideally, microdata could be released in such a way that a balance between usefulness of the data and privacy is struck. This paper presents a review of proposed methods of statistical disclosure control and techniques for assessing the privacy of such methods under different definitions of disclosure.

References:
Abowd, J., Woodcock, S., 2001. Disclosure limitation in longitudinal linked data. Confidentiality, Disclosure, and Data Access: Theory and Practical Applications for Statistical Agencies, 215–277.

Adam, N.R., Worthmann, J.C., 1989. Security-control methods for statistical databases: a comparative study. ACM Comput. Surv. 21 (4), 515–556.

Armstrong, M., Rushton, G., Zimmerman, D.L., 1999. Geographically masking health data to preserve confidentiality. Statistics in Medicine 18 (5), 497–525.

Bethlehem, J.G., Keller, W., Pannekoek, J., 1990. Disclosure control of microdata. Jorunal of the American Statistical Association 85, 38–45.

Blum, A., Dwork, C., McSherry, F., Nissam, K., 2005. Practical privacy: The sulq framework. In: Proceedings of the 24th ACM SIGMOD-SIGACT-SIGART Symposium on Principles of Database Systems. pp. 128–138.

Bowden, R.J., Sim, A.B., 1992. The privacy bootstrap. Journal of Business and Economic Statistics 10 (3), 337–345.

Carlson, M., Salabasis, M., 2002. A data-swapping technique for generating synthetic samples; a method for disclosure control. Res. Official Statist. (5), 35–64.

Cox, L.H., 1980. Suppression methodology and statistical disclosure control. Journal of the American Statistical Association 75, 377–385.

Cox, L.H., 1984. Disclosure control methods for frequency count data. Tech. rep., U.S. Bureau of the Census.

Cox, L.H., 1987. A constructive procedure for unbiased controlled rounding. Journal of the American Statistical Association 82, 520–524.

Cox, L.H., 1994. Matrix masking methods for disclosure limitation in microdata. Survey Methodology 6, 165–169.

Cox, L.H., Fagan, J.T., Greenberg, B., Hemmig, R., 1987. Disclosure avoidance techniques for tabular data. Tech. rep., U.S. Bureau of the Census.

Dalenius, T., 1977. Towards a methodology for statistical disclosure control. Statistik Tidskrift 15, 429–444.

Dalenius, T., 1986. Finding a needle in a haystack - or identifying anonymous census record. Journal of Official Statistics 2 (3), 329–336.

Dalenius, T., Denning, D., 1982. A hybrid scheme for release of statistics. Statistisk Tidskrift.

Dalenius, T., Reiss, S.P., 1982. Data-swapping: A technique for disclosure control. Journal of Statistical Planning and Inference 6, 73–85.

De Waal, A., Hundepool, A., Willenborg, L., 1995. Argus: Software for statistical disclosure control of microdata. U.S. Census Bureau.

DeGroot, M.H., 1962. Uncertainty, information, and sequential experiments. Annals of Mathematical Statistics 33, 404–419.

DeGroot, M.H., 1970. Optimal Statistical Decisions. Mansell, London.

Dinur, I., Nissam, K., 2003. Revealing information while preserving privacy. In: Proceedings of the 22nd ACM SIGMOD-SIGACT-SIGART Symposium on Principlesof Database Systems. pp. 202–210.

Domingo-Ferrer, J., Torra, V., 2001a. A Quantitative Comparison of Disclosure Control Methods for Microdata. In: Doyle, P., Lane, J., Theeuwes, J., Zayatz, L. (Eds.), Confidentiality, Disclosure and Data Access - Theory and Practical Applications for Statistical Agencies. North-Holland, Amsterdam, Ch. 6, pp. 113–135.

Domingo-Ferrer, J., Torra, V., 2001b. Disclosure control methods and information loss for microdata. In: Doyle, P., Lane, J., Theeuwes, J., Zayatz, L. (Eds.), Confidentiality, Disclosure and Data Access - Theory and Practical Applications for Statistical Agencies. North-Holland, Amsterdam, Ch. 5, pp. 93–112.

Duncan, G., Lambert, D., 1986. Disclosure-limited data dissemination. Journal of the American Statistical Association 81, 10–28.

Duncan, G., Lambert, D., 1989. The risk of disclosure for microdata. Journal of Business & Economic Statistics 7, 207–217.

Duncan, G., Pearson, R., 1991. Enhancing access to microdata while protecting confidentiality: prospects for the future (with discussion). Statistical Science 6, 219–232.

Dwork, C., 2006. Differential privacy. In: ICALP. Springer, pp. 1–12.

Dwork, C., 2008. An ad omnia approach to defining and achieving private data analysis. In: Lecture Notes in Computer Science. Springer, p. 10.

Dwork, C., Lei, J., 2009. Differential privacy and robust statistics. In: Proceedings of the 41th Annual ACM Symposium on Theory of Computing (STOC). pp. 371–380.

Dwork, C., Mcsherry, F., Nissim, K., Smith, A., 2006. Calibrating noise to sensitivity in private data analysis. In: Proceedings of the 3rd Theory of Cryptography Conference. Springer, pp. 265–284.

Dwork, C., Nissam, K., 2004. Privacy-preserving datamining on vertically partitioned databases. In: Advances in Cryptology: Proceedings of Crypto. pp. 528–544.

Elliot, M., 2000. DIS: a new approach to the measurement of statistical disclosure risk. International Journal of Risk Assessment and Management 2, 39–48.

Federal Committee on Statistical Methodology (FCSM), 2005. Statistical policy working group 22 - report on statistical disclosure limitation methodology. U.S. Census Bureau.

Fellegi, I.P., 1972. On the question of statistical confidentiality. Journal of the American Statistical Association 67 (337), 7–18.

Fienberg, S.E., McIntyre, J., 2004. Data swapping: Variations on a theme by Dalenius and Reiss. In: Domingo-Ferrer, J., Torra, V. (Eds.), Privacy in Statistical Databases. Vol. 3050 of Lecture Notes in Computer Science. Springer Berlin/Heidelberg, pp. 519, http://dx.doi.org/10.1007/ 978-3-540-25955-8_2

Fuller, W., 1993. Masking procedurse for microdata disclosure limitation. Journal of Official Statistics 9, 383–406.

General Assembly of the United Nations, 1948. Universal declaration of human rights.

Gouweleeuw, J., P. Kooiman, L.W., de Wolf, P.-P., 1998. Post randomisation for statistical disclosure control: Theory and implementation. Journal of Official Statistics 14 (4), 463–478.

Greenberg, B., 1987. Rank swapping for masking ordinal microdata. Tech. rep., U.S. Bureau of the Census (unpublished manuscript), Suitland, Maryland, USA.

Greenberg, B.G., Abul-Ela, A.-L.A., Simmons, W.R., Horvitz, D.G., 1969. The unrelated question randomized response model: Theoretical framework. Journal of the American Statistical Association 64 (326), 520–539.

Harel, O., Zhou, X.-H., 2007. Multiple imputation: Review and theory, implementation and software. Statistics in Medicine 26, 3057–3077.

Hundepool, A., Domingo-ferrer, J., Franconi, L., Giessing, S., Lenz, R., Longhurst, J., Nordholt, E.S., Seri, G., paul De Wolf, P., 2006. A CENtre of EXcellence for Statistical Disclosure Control Handbook on Statistical Disclosure Control Version 1.01.

Hundepool, A., Wetering, A. v.d., Ramaswamy, R., Wolf, P.d., Giessing, S., Fischetti, M., Salazar, J., Castro, J., Lowthian, P., Feb. 2005. τ-argus 3.1 user manual. Statistics Netherlands, Voorburg NL.

Hundepool, A., Willenborg, L., 1996. μ- and τ-argus: Software for statistical disclosure control. Third International Seminar on Statistical Confidentiality, Bled.

Karr, A., Kohnen, C.N., Oganian, A., Reiter, J.P., Sanil, A.P., 2006. A framework for evaluating the utility of data altered to protect confidentiality. American Statistician 60 (3), 224–232.

Kaufman, S., Seastrom, M., Roey, S., 2005. Do disclosure controls to protect confidentiality degrade the quality of the data? In: American Statistical Association, Proceedings of the Section on Survey Research.

Kennickell, A.B., 1997. Multiple imputation and disclosure protection: the case of the 1995 survey of consumer finances. Record Linkage Techniques, 248–267.

Kim, J., 1986. Limiting disclosure in microdata based on random noise and transformation. Bureau of the Census.

Krumm, J., 2007. Inference attacks on location tracks. Proceedings of Fifth International Conference on Pervasive Computingy, 127–143.

Li, N., Li, T., Venkatasubramanian, S., 2007. t-closeness: Privacy beyond k-anonymity and l-diversity. In: Data Engineering, 2007. ICDE 2007. IEEE 23rd International Conference on. pp. 106–115.

Liew, C.K., Choi, U.J., Liew, C.J., 1985. A data distortion by probability distribution. ACM Trans. Database Syst. 10 (3), 395–411.

Little, R.J.A., 1993. Statistical analysis of masked data. Journal of Official Statistics 9, 407–426.

Little, R.J.A., Rubin, D.B., 1987. Statistical Analysis with Missing Data. John Wiley & Sons.

Liu, F., Little, R.J.A., 2002. Selective multiple mputation of keys for statistical disclosure control in microdata. In: Proceedings Joint Statistical Meet. pp. 2133–2138.

Machanavajjhala, A., Kifer, D., Abowd, J., Gehrke, J., Vilhuber, L., April 2008. Privacy: Theory meets practice on the map. In: International Conference on Data Engineering. Cornell University Comuputer Science Department, Cornell, USA, p. 10.

Machanavajjhala, A., Kifer, D., Gehrke, J., Venkitasubramaniam, M., 2007. L-diversity: Privacy beyond k-anonymity. ACM Trans. Knowl. Discov. Data 1 (1), 3.

Manning, A.M., Haglin, D.J., Keane, J.A., 2008. A recursive search algorithm for statistical disclosure assessment. Data Min. Knowl. Discov. 16 (2), 165–196.

Marsh, C., Skinner, C., Arber, S., Penhale, B., Openshaw, S., Hobcraft, J., Lievesley, D., Walford, N., 1991. The case for samples of anonymized records from the 1991 census. Journal of the Royal Statistical Society 154 (2), 305–340.

Matthews, G.J., Harel, O., Aseltine, R.H., 2010a. Assessing database privacy using the area under the receiver-operator characteristic curve. Health Services and Outcomes Research Methodology 10 (1), 1–15.

Matthews, G.J., Harel, O., Aseltine, R.H., 2010b. Examining the robustness of fully synthetic data techniques for data with binary variables. Journal of Statistical Computation and Simulation 80 (6), 609–624.

Moore, Jr., R., 1996. Controlled data-swapping techniques for masking public use microdata. Census Tech Report.

Mugge, R., 1983. Issues in protecting confidentiality in national health statistics. Proceedings of the Section on Survey Research Methods.

Nissim, K., Raskhodnikova, S., Smith, A., 2007. Smooth sensitivity and sampling in private data analysis. In: STOC ’07: Proceedings of the thirty-ninth annual ACM symposium on Theory of computing. pp. 75–84.

Paass, G., 1988. Disclosure risk and disclosure avoidance for microdata. Journal of Business and Economic Statistics 6 (4), 487–500.

Palley, M., Simonoff, J., 1987. The use of regression methodology for the compromise of confidential information in statistical databases. ACM Trans. Database Systems 12 (4), 593–608.

Raghunathan, T.E., Reiter, J.P., Rubin, D.B., 2003. Multiple imputation for statistical disclosure limitation. Journal of Official Statistics 19 (1), 1–16.

Rajasekaran, S., Harel, O., Zuba, M., Matthews, G.J., Aseltine, Jr., R., 2009. Responsible data releases. In: Proceedings 9th Industrial Conference on Data Mining (ICDM). Springer LNCS, pp. 388–400.

Reiss, S.P., 1984. Practical data-swapping: The first steps. CM Transactions on Database Systems 9, 20–37.

Reiter, J.P., 2002. Satisfying disclosure restriction with synthetic data sets. Journal of Official Statistics 18 (4), 531–543.

Reiter, J.P., 2003. Inference for partially synthetic, public use microdata sets. Survey Methodology 29 (2), 181–188.

Reiter, J.P., 2004a. New approaches to data dissemination: A glimpse into the future (?). Chance 17 (3), 11–15.

Reiter, J.P., 2004b. Simultaneous use of multiple imputation for missing data and disclosure limitation. Survey Methodology 30 (2), 235–242.

Reiter, J.P., 2005a. Estimating risks of identification disclosure in microdata. Journal of the American Statistical Association 100, 1103–1112.

Reiter, J.P., 2005b. Releasing multiply imputed, synthetic public use microdata: An illustration and empirical study. Journal of the Royal Statistical Society, Series A: Statistics in Society 168 (1), 185–205.

Reiter, J.P., 2005c. Using CART to generate partially synthetic public use microdata. Journal of Official Statistics 21 (3), 441–462.

Rubin, D.B., 1987. Multiple Imputation for Nonresponse in Surveys. John Wiley & Sons.

Rubin, D.B., 1993. Comment on “Statistical disclosure limitation”. Journal of Official Statistics 9, 461–468.

Rubner, Y., Tomasi, C., Guibas, L.J., 1998. A metric for distributions with applications to image databases. Computer Vision, IEEE International Conference on 0, 59.

Sarathy, R., Muralidhar, K., 2002a. The security of confidential numerical data in databases. Information Systems Research 13 (4), 389–403.

Sarathy, R., Muralidhar, K., 2002b. The security of confidential numerical data in databases. Info. Sys. Research 13 (4), 389–403.

Schafer, J.L., Graham, J.W., 2002. Missing data: Our view of state of the art. Psychological Methods 7 (2), 147–177.

Singh, A., Yu, F., Dunteman, G., 2003. MASSC: A new data mask for limiting statistical information loss and disclosure. In: Proceedings of the Joint UNECE/EUROSTAT Work Session on Statistical Data Confidentiality. pp. 373–394.

Skinner, C., 2009. Statistical disclosure control for survey data. In: Pfeffermann, D and Rao, C.R. eds. Handbook of Statistics Vol. 29A: Sample Surveys: Design, Methods and Applications. pp. 381–396.

Skinner, C., Marsh, C., Openshaw, S., Wymer, C., 1994. Disclosure control for census microdata. Journal of Official Statistics 10, 31–51.

Skinner, C., Shlomo, N., 2008. Assessing identification risk in survey microdata using log-linear models. Journal of the American Statistical Association 103, 989–1001.

Skinner, C.J., Elliot, M.J., 2002. A measure of disclosure risk for microdata. Journal of the Royal Statistical Society. Series B (Statistical Methodology) 64 (4), 855–867.

Smith, A., 2008. Efficient, dfferentially private point estimators. arXiv:0809.4794v1 [cs.CR].

Spruill, N.L., 1982. Measures of confidentiality. Statistics of Income and Related Administrative Record Research, 131–136.

Spruill, N.L., 1983. The confidentiality and analytic usefulness of masked business microdata. In: Proceedings of the Section on Survey Reserach Microdata. American Statistical Association, pp. 602–607.

Sweeney, L., 1996. Replacing personally-identifying information in medical records, the scrub system. In: American Medical Informatics Association. Hanley and Belfus, Inc., pp. 333–337.

Sweeney, L., 1997. Guaranteeing anonymity when sharing medical data, the datafly system. Journal of the American Medical Informatics Association 4, 51–55.

Sweeney, L., 2002a. Achieving k-anonymity privacy protection using generalization and suppression. International Journal of Uncertainty, Fuzziness and Knowledge Based Systems 10 (5), 571–588.

Sweeney, L., 2002b. k-anonymity: A model for protecting privacy. International Journal of Uncertainty, Fuzziness and Knowledge Based Systems 10 (5), 557–570.

Tendick, P., 1991. Optimal noise addition for preserving confidentiality in multivariate data. Journal of Statistical Planning and Inference 27 (2), 341–353.

United Nations Economic Comission for Europe (UNECE), 2007. Manging statistical cinfidentiality and microdata access: Principles and guidlinesof good practice.

Warner, S.L., 1965. Randomized response: A survey technique for eliminating evasive answer bias. Journal of the American Statistical Association 60 (309), 63–69.

Wasserman, L., Zhou, S., 2010. A statistical framework for differential privacy. Journal of the American Statistical Association 105 (489), 375–389.

Willenborg, L., de Waal, T., 2001. Elements of Statistical Disclosure Control. Springer-Verlag.

Woodward, B., 1995. The computer-based patient record and confidentiality. The New England Journal of Medicine, 1419–1422.

A. Philip Dawid, Vanessa Didelez

Source: Statist. Surv., Volume 4, 184--231.

Abstract:
We consider the problem of learning about and comparing the consequences of dynamic treatment strategies on the basis of observational data. We formulate this within a probabilistic decision-theoretic framework. Our approach is compared with related work by Robins and others: in particular, we show how Robins’s ‘ G -computation’ algorithm arises naturally from this decision-theoretic perspective. Careful attention is paid to the mathematical and substantive conditions required to justify the use of this formula. These conditions revolve around a property we term stability , which relates the probabilistic behaviours of observational and interventional regimes. We show how an assumption of ‘sequential randomization’ (or ‘no unmeasured confounders’), or an alternative assumption of ‘sequential irrelevance’, can be used to infer stability. Probabilistic influence diagrams are used to simplify manipulations, and their power and limitations are discussed. We compare our approach with alternative formulations based on causal DAGs or potential response models. We aim to show that formulating the problem of assessing dynamic treatment strategies as a problem of decision analysis brings clarity, simplicity and generality.

References:
Arjas, E. and Parner, J. (2004). Causal reasoning from longitudinal data. Scandinavian Journal of Statistics 31 171–187.

Arjas, E. and Saarela, O. (2010). Optimal dynamic regimes: Presenting a case for predictive inference. The International Journal of Biostatistics 6. http://tinyurl.com/33dfssf

Cowell, R. G., Dawid, A. P., Lauritzen, S. L. and Spiegelhalter, D. J. (1999). Probabilistic Networks and Expert Systems. Springer, New York.

Dawid, A. P. (1979). Conditional independence in statistical theory (with Discussion). Journal of the Royal Statistical Society, Series B 41 1–31.

Dawid, A. P. (1992). Applications of a general propagation algorithm for probabilistic expert systems. Statistics and Computing 2 25–36.

Dawid, A. P. (1998). Conditional independence. In Encyclopedia of Statistical Science ({U}pdate Volume 2) ( S. Kotz, C. B. Read and D. L. Banks, eds.) 146–155. Wiley-Interscience, New York.

Dawid, A. P. (2000). Causal inference without counterfactuals (with Discussion). Journal of the American Statistical Association 95 407–448.

Dawid, A. P. (2001). Separoids: A mathematical framework for conditional independence and irrelevance. Annals of Mathematics and Artificial Intelligence 32 335–372.

Dawid, A. P. (2002). Influence diagrams for causal modelling and inference. International Statistical Review 70 161–189. Corrigenda, ibid ., 437.

Dawid, A. P. (2003). Causal inference using influence diagrams: The problem of partial compliance (with Discussion). In Highly Structured Stochastic Systems ( P. J. Green, N. L. Hjort and S. Richardson, eds.) 45–81. Oxford University Press.

Dawid, A. P. (2010). Beware of the DAG! In Proceedings of the NIPS 2008 Workshop on Causality. Journal of Machine Learning Research Workshop and Conference Proceedings ( D. Janzing, I. Guyon and B. Schölkopf, eds.) 6 59–86. http://tinyurl.com/33va7tm

Dawid, A. P. and Didelez, V. (2008). Identifying optimal sequential decisions. In Proceedings of the Twenty-Fourth Annual Conference on Uncertainty in Artificial Intelligence (UAI-08) ( D. McAllester and A. Nicholson, eds.). 113-120. AUAI Press, Corvallis, Oregon. http://tinyurl.com/3899qpp

Dechter, R. (2003). Constraint Processing. Morgan Kaufmann Publishers.

Didelez, V., Dawid, A. P. and Geneletti, S. G. (2006). Direct and indirect effects of sequential treatments. In Proceedings of the Twenty-Second Annual Conference on Uncertainty in Artificial Intelligence (UAI-06) ( R. Dechter and T. Richardson, eds.). 138-146. AUAI Press, Arlington, Virginia. http://tinyurl.com/32w3f4e

Didelez, V., Kreiner, S. and Keiding, N. (2010). Graphical models for inference under outcome dependent sampling. Statistical Science (to appear).

Didelez, V. and Sheehan, N. S. (2007). Mendelian randomisation: Why epidemiology needs a formal language for causality. In Causality and Probability in the Sciences, ( F. Russo and J. Williamson, eds.). Texts in Philosophy Series 5 263–292. College Publications, London.

Eichler, M. and Didelez, V. (2010). Granger-causality and the effect of interventions in time series. Lifetime Data Analysis 16 3–32.

Ferguson, T. S. (1967). Mathematical Statistics: A Decision Theoretic Approach. Academic Press, New York, London.

Geneletti, S. G. (2007). Identifying direct and indirect effects in a non–counterfactual framework. Journal of the Royal Statistical Society: Series B 69 199–215.

Geneletti, S. G. and Dawid, A. P. (2010). Defining and identifying the effect of treatment on the treated. In Causality in the Sciences ( P. M. Illari, F. Russo and J. Williamson, eds.) Oxford University Press (to appear).

Gill, R. D. and Robins, J. M. (2001). Causal inference for complex longitudinal data: The continuous case. Annals of Statistics 29 1785–1811.

Guo, H. and Dawid, A. P. (2010). Sufficient covariates and linear propensity analysis. In Proceedings of the Thirteenth International Workshop on Artificial Intelligence and Statistics, (AISTATS) 2010, Chia Laguna, Sardinia, Italy, May 13-15, 2010. Journal of Machine Learning Research Workshop and Conference Proceedings ( Y. W. Teh and D. M. Titterington, eds.) 9 281–288. http://tinyurl.com/33lmuj7

Henderson, R., Ansel, P. and Alshibani, D. (2010). Regret-regression for optimal dynamic treatment regimes. Biometrics (to appear). doi:10.1111/j.1541-0420.2009.01368.x

Hernán, M. A. and Taubman, S. L. (2008). Does obesity shorten life? The importance of well defined interventions to answer causal questions. International Journal of Obesity 32 S8–S14.

Holland, P. W. (1986). Statistics and causal inference (with Discussion). Journal of the American Statistical Association 81 945–970.

Huang, Y. and Valtorta, M. (2006). Identifiability in causal Bayesian networks: A sound and complete algorithm. In AAAI’06: Proceedings of the 21st National Conference on Artificial Intelligence 1149–1154. AAAI Press.

Kang, J. D. Y. and Schafer, J. L. (2007). Demystifying double robustness: A comparison of alternative strategies for estimating a population mean from incomplete data. Statistical Science 22 523–539.

Lauritzen, S. L., Dawid, A. P., Larsen, B. N. and Leimer, H. G. (1990). Independence properties of directed Markov fields. Networks 20 491–505.

Lok, J., Gill, R., van der Vaart, A. and Robins, J. (2004). Estimating the causal effect of a time-varying treatment on time-to-event using structural nested failure time models. Statistica Neerlandica 58 271–295.

Moodie, E. M., Richardson, T. S. and Stephens, D. A. (2007). Demystifying optimal dynamic treatment regimes. Biometrics 63 447–455.

Murphy, S. A. (2003). Optimal dynamic treatment regimes (with Discussion). Journal of the Royal Statistical Society, Series B 65 331-366.

Oliver, R. M. and Smith, J. Q., eds. (1990). Influence Diagrams, Belief Nets and Decision Analysis. John Wiley and Sons, Chichester, United Kingdom.

Pearl, J. (1995). Causal diagrams for empirical research (with Discussion). Biometrika 82 669-710.

Pearl, J. (2009). Causality: Models, Reasoning and Inference, Second ed. Cambridge University Press, Cambridge.

Pearl, J. and Paz, A. (1987). Graphoids: A graph-based logic for reasoning about relevance relations. In Advances in Artificial Intelligence ( D. Hogg and L. Steels, eds.) II 357–363. North-Holland, Amsterdam.

Pearl, J. and Robins, J. (1995). Probabilistic evaluation of sequential plans from causal models with hidden variables. In Proceedings of the 11th Conference on Uncertainty in Artificial Intelligence ( P. Besnard and S. Hanks, eds.) 444–453. Morgan Kaufmann Publishers, San Francisco.

Raiffa, H. (1968). Decision Analysis. Addison-Wesley, Reading, Massachusetts.

Robins, J. M. (1986). A new approach to causal inference in mortality studies with sustained exposure periods—Application to control of the healthy worker survivor effect. Mathematical Modelling 7 1393–1512.

Robins, J. M. (1987). Addendum to “A new approach to causal inference in mortality studies with sustained exposure periods—Application to control of the healthy worker survivor effect”. Computers & Mathematics with Applications 14 923–945.

Robins, J. M. (1989). The analysis of randomized and nonrandomized AIDS treatment trials using a new approach to causal inference in longitudinal studies. In Health Service Research Methodology: A Focus on AIDS ( L. Sechrest, H. Freeman and A. Mulley, eds.) 113–159. NCSHR, U.S. Public Health Service.

Robins, J. M. (1992). Estimation of the time-dependent accelerated failure time model in the presence of confounding factors. Biometrika 79 321–324.

Robins, J. M. (1997). Causal inference from complex longitudinal data. In Latent Variable Modeling and Applications to Causality, ( M. Berkane, ed.). Lecture Notes in Statistics 120 69–117. Springer-Verlag, New York.

Robins, J. M. (1998). Structural nested failure time models. In Survival Analysis, ( P. K. Andersen and N. Keiding, eds.). Encyclopedia of Biostatistics 6 4372–4389. John Wiley and Sons, Chichester, UK.

Robins, J. M. (2000). Robust estimation in sequentially ignorable missing data and causal inference models. In Proceedings of the American Statistical Association Section on Bayesian Statistical Science 1999 6–10.

Robins, J. M. (2004). Optimal structural nested models for optimal sequential decisions. In Proceedings of the Second Seattle Symposium on Biostatistics ( D. Y. Lin and P. Heagerty, eds.) 189–326. Springer, New York.

Robins, J. M., Greenland, S. and Hu, F. C. (1999). Estimation of the causal effect of a time-varying exposure on the marginal mean of a repeated binary outcome. Journal of the American Statistical Association 94 687–700.

Robins, J. M., Hernán, M. A. and Brumback, B. (2000). Marginal structural models and causal inference in epidemiology. Epidemiology 11 550–560.

Robins, J. M. and Wasserman, L. A. (1997). Estimation of effects of sequential treatments by reparameterizing directed acyclic graphs. In Proceedings of the 13th Annual Conference on Uncertainty in Artificial Intelligence ( D. Geiger and P. Shenoy, eds.) 409-420. Morgan Kaufmann Publishers, San Francisco. http://tinyurl.com/33ghsas

Rosthøj, S., Fullwood, C., Henderson, R. and Stewart, S. (2006). Estimation of optimal dynamic anticoagulation regimes from observational data: A regret-based approach. Statistics in Medicine 25 4197–4215.

Shpitser, I. and Pearl, J. (2006a). Identification of conditional interventional distributions. In Proceedings of the 22nd Annual Conference on Uncertainty in Artificial Intelligence (UAI-06) ( R. Dechter and T. Richardson, eds.). 437–444. AUAI Press, Corvallis, Oregon. http://tinyurl.com/2um8w47

Shpitser, I. and Pearl, J. (2006b). Identification of joint interventional distributions in recursive semi-Markovian causal models. In Proceedings of the Twenty-First National Conference on Artificial Intelligence 1219–1226. AAAI Press, Menlo Park, California.

Spirtes, P., Glymour, C. and Scheines, R. (2000). Causation, Prediction and Search, Second ed. Springer-Verlag, New York.

Sterne, J. A. C., May, M., Costagliola, D., de Wolf, F., Phillips, A. N., Harris, R., Funk, M. J., Geskus, R. B., Gill, J., Dabis, F., Miro, J. M., Justice, A. C., Ledergerber, B., Fatkenheuer, G., Hogg, R. S., D’Arminio-Monforte, A., Saag, M., Smith, C., Staszewski, S., Egger, M., Cole, S. R. and When To Start Consortium (2009). Timing of initiation of antiretroviral therapy in AIDS-Free HIV-1-infected patients: A collaborative analysis of 18 HIV cohort studies. Lancet 373 1352–1363.

Taubman, S. L., Robins, J. M., Mittleman, M. A. and Hernán, M. A. (2009). Intervening on risk factors for coronary heart disease: An application of the parametric g-formula. International Journal of Epidemiology 38 1599–1611.

Tian, J. (2008). Identifying dynamic sequential plans. In Proceedings of the Twenty-Fourth Annual Conference on Uncertainty in Artificial Intelligence (UAI-08) ( D. McAllester and A. Nicholson, eds.). 554–561. AUAI Press, Corvallis, Oregon. http://tinyurl.com/36ufx2h

Verma, T. and Pearl, J. (1990). Causal networks: Semantics and expressiveness. In Uncertainty in Artificial Intelligence 4 ( R. D. Shachter, T. S. Levitt, L. N. Kanal and J. F. Lemmer, eds.) 69–76. North-Holland, Amsterdam.

Sophie Achard, Jean-François Coeurjolly

Source: Statist. Surv., Volume 4, 117--147.

Abstract:
This paper gives an overview of the problem of estimating the Hurst parameter of a fractional Brownian motion when the data are observed with outliers and/or with an additive noise by using methods based on discrete variations. We show that the classical estimation procedure based on the log-linearity of the variogram of dilated series is made more robust to outliers and/or an additive noise by considering sample quantiles and trimmed means of the squared series or differences of empirical variances. These different procedures are compared and discussed through a large simulation study and are implemented in the R package dvfBm.

Michael P. Fay, Michael A. Proschan

Source: Statist. Surv., Volume 4, 1--39.

Abstract:
In a mathematical approach to hypothesis tests, we start with a clearly defined set of hypotheses and choose the test with the best properties for those hypotheses. In practice, we often start with less precise hypotheses. For example, often a researcher wants to know which of two groups generally has the larger responses, and either a t-test or a Wilcoxon-Mann-Whitney (WMW) test could be acceptable. Although both t-tests and WMW tests are usually associated with quite different hypotheses, the decision rule and p-value from either test could be associated with many different sets of assumptions, which we call perspectives. It is useful to have many of the different perspectives to which a decision rule may be applied collected in one place, since each perspective allows a different interpretation of the associated p-value. Here we collect many such perspectives for the two-sample t-test, the WMW test and other related tests. We discuss validity and consistency under each perspective and discuss recommendations between the tests in light of these many different perspectives. Finally, we briefly discuss a decision rule for testing genetic neutrality where knowledge of the many perspectives is vital to the proper interpretation of the decision rule.

We show, by an explicit construction, that a mixture of univariate Gaussians with variance 1 and means in $[-A,A]$ can have $Omega(A^2)$ modes. This disproves a recent conjecture of Dytso, Yagli, Poor and Shamai [IEEE Trans. Inform. Theory, Apr. 2020], who showed that such a mixture can have at most $O(A^2)$ modes and surmised that the upper bound could be improved to $O(A)$. Our result holds even if an additional variance constraint is imposed on the mixing distribution. Extending the result to higher dimensions, we exhibit a mixture of Gaussians in $mathbb{R}^d$, with identity covariances and means inside $[-A,A]^d$, that has $Omega(A^{2d})$ modes.

The transfer learning technique is widely used to learning in one context and applying it to another, i.e. the capacity to apply acquired knowledge and skills to new situations. But is it possible to transfer the learning from a deep neural network to a weaker neural network? Is it possible to improve the performance of a weak neural network using the knowledge acquired by a more powerful neural network? In this work, during the training process of a weak network, we add a loss function that minimizes the distance between the features previously learned from a strong neural network with the features that the weak network must try to learn. To demonstrate the effectiveness and robustness of our approach, we conducted a large number of experiments using three known datasets and demonstrated that a weak neural network can increase its performance if its learning process is driven by a more powerful neural network.

Official counts of COVID-19 deaths have been criticized for potentially including people who did not die of COVID-19 but merely died with COVID-19. I address that critique by fitting a generalized additive model to weekly counts of all registered deaths in England and Wales during the 2010s. The model produces baseline rates of death registrations expected in the absence of the COVID-19 pandemic, and comparing those baselines to recent counts of registered deaths exposes the emergence of excess deaths late in March 2020. Among adults aged 45+, about 38,700 excess deaths were registered in the 5 weeks comprising 21 March through 24 April (612 $pm$ 416 from 21$-$27 March, 5675 $pm$ 439 from 28 March through 3 April, then 9183 $pm$ 468, 12,712 $pm$ 589, and 10,511 $pm$ 567 in April's next 3 weeks). Both the Office for National Statistics's respective count of 26,891 death certificates which mention COVID-19, and the Department of Health and Social Care's hospital-focused count of 21,222 deaths, are appreciably less, implying that their counting methods have underestimated rather than overestimated the pandemic's true death toll. If underreporting rates have held steady, about 45,900 direct and indirect COVID-19 deaths might have been registered by April's end but not yet publicly reported in full.

Cooperation between different data owners may lead to an improvement in forecast quality - for instance by benefiting from spatial-temporal dependencies in geographically distributed time series. Due to business competitive factors and personal data protection questions, said data owners might be unwilling to share their data, which increases the interest in collaborative privacy-preserving forecasting. This paper analyses the state-of-the-art and unveils several shortcomings of existing methods in guaranteeing data privacy when employing Vector Autoregressive (VAR) models. The paper also provides mathematical proofs and numerical analysis to evaluate existing privacy-preserving methods, dividing them into three groups: data transformation, secure multi-party computations, and decomposition methods. The analysis shows that state-of-the-art techniques have limitations in preserving data privacy, such as a trade-off between privacy and forecasting accuracy, while the original data in iterative model fitting processes, in which intermediate results are shared, can be inferred after some iterations.

Spatial trajectories are ubiquitous and complex signals. Their analysis is crucial in many research fields, from urban planning to neuroscience. Several approaches have been proposed to cluster trajectories. They rely on hand-crafted features, which struggle to capture the spatio-temporal complexity of the signal, or on Artificial Neural Networks (ANNs) which can be more efficient but less interpretable. In this paper we present a novel ANN architecture designed to capture the spatio-temporal patterns characteristic of a set of trajectories, while taking into account the demographics of the navigators. Hence, our model extracts markers linked to both behaviour and demographics. We propose a composite signal analyser (CompSNN) combining three simple ANN modules. Each of these modules uses different signal representations of the trajectory while remaining interpretable. Our CompSNN performs significantly better than its modules taken in isolation and allows to visualise which parts of the signal were most useful to discriminate the trajectories.

In recent years, multi-access edge computing (MEC) is a key enabler for handling the massive expansion of Internet of Things (IoT) applications and services. However, energy consumption of a MEC network depends on volatile tasks that induces risk for energy demand estimations. As an energy supplier, a microgrid can facilitate seamless energy supply. However, the risk associated with energy supply is also increased due to unpredictable energy generation from renewable and non-renewable sources. Especially, the risk of energy shortfall is involved with uncertainties in both energy consumption and generation. In this paper, we study a risk-aware energy scheduling problem for a microgrid-powered MEC network. First, we formulate an optimization problem considering the conditional value-at-risk (CVaR) measurement for both energy consumption and generation, where the objective is to minimize the loss of energy shortfall of the MEC networks and we show this problem is an NP-hard problem. Second, we analyze our formulated problem using a multi-agent stochastic game that ensures the joint policy Nash equilibrium, and show the convergence of the proposed model. Third, we derive the solution by applying a multi-agent deep reinforcement learning (MADRL)-based asynchronous advantage actor-critic (A3C) algorithm with shared neural networks. This method mitigates the curse of dimensionality of the state space and chooses the best policy among the agents for the proposed problem. Finally, the experimental results establish a significant performance gain by considering CVaR for high accuracy energy scheduling of the proposed model than both the single and random agent models.

Multi-Class Incremental Learning (MCIL) aims to learn new concepts by incrementally updating a model trained on previous concepts. However, there is an inherent trade-off to effectively learning new concepts without catastrophic forgetting of previous ones. To alleviate this issue, it has been proposed to keep around a few examples of the previous concepts but the effectiveness of this approach heavily depends on the representativeness of these examples. This paper proposes a novel and automatic framework we call mnemonics, where we parameterize exemplars and make them optimizable in an end-to-end manner. We train the framework through bilevel optimizations, i.e., model-level and exemplar-level. We conduct extensive experiments on three MCIL benchmarks, CIFAR-100, ImageNet-Subset and ImageNet, and show that using mnemonics exemplars can surpass the state-of-the-art by a large margin. Interestingly and quite intriguingly, the mnemonics exemplars tend to be on the boundaries between different classes.

Attribution methods provide insights into the decision-making of machine learning models like artificial neural networks. For a given input sample, they assign a relevance score to each individual input variable, such as the pixels of an image. In this work we adapt the information bottleneck concept for attribution. By adding noise to intermediate feature maps we restrict the flow of information and can quantify (in bits) how much information image regions provide. We compare our method against ten baselines using three different metrics on VGG-16 and ResNet-50, and find that our methods outperform all baselines in five out of six settings. The method's information-theoretic foundation provides an absolute frame of reference for attribution values (bits) and a guarantee that regions scored close to zero are not necessary for the network's decision. For reviews: https://openreview.net/forum?id=S1xWh1rYwB For code: https://github.com/BioroboticsLab/IBA

We focus on estimating emph{a priori} generalization error of two-layer ReLU neural networks (NNs) trained by mean squared error, which only depends on initial parameters and the target function, through the following research line. We first estimate emph{a priori} generalization error of finite-width two-layer ReLU NN with constraint of minimal norm solution, which is proved by cite{zhang2019type} to be an equivalent solution of a linearized (w.r.t. parameter) finite-width two-layer NN. As the width goes to infinity, the linearized NN converges to the NN in Neural Tangent Kernel (NTK) regime citep{jacot2018neural}. Thus, we can derive the emph{a priori} generalization error of two-layer ReLU NN in NTK regime. The distance between NN in a NTK regime and a finite-width NN with gradient training is estimated by cite{arora2019exact}. Based on the results in cite{arora2019exact}, our work proves an emph{a priori} generalization error bound of two-layer ReLU NNs. This estimate uses the intrinsic implicit bias of the minimum norm solution without requiring extra regularity in the loss function. This emph{a priori} estimate also implies that NN does not suffer from curse of dimensionality, and a small generalization error can be achieved without requiring exponentially large number of neurons. In addition the research line proposed in this paper can also be used to study other properties of the finite-width network, such as the posterior generalization error.

A graph homomorphism is a map between two graphs that preserves adjacency relations. We consider the problem of sampling a random graph homomorphism from a graph $F$ into a large network $mathcal{G}$. We propose two complementary MCMC algorithms for sampling a random graph homomorphisms and establish bounds on their mixing times and concentration of their time averages. Based on our sampling algorithms, we propose a novel framework for network data analysis that circumvents some of the drawbacks in methods based on independent and neigborhood sampling. Various time averages of the MCMC trajectory give us various computable observables, including well-known ones such as homomorphism density and average clustering coefficient and their generalizations. Furthermore, we show that these network observables are stable with respect to a suitably renormalized cut distance between networks. We provide various examples and simulations demonstrating our framework through synthetic networks. We also apply our framework for network clustering and classification problems using the Facebook100 dataset and Word Adjacency Networks of a set of classic novels.

A deep neural network has relieved the burden of feature engineering by human experts, but comparable efforts are instead required to determine an effective architecture. On the other hands, as the size of a network has over-grown, a lot of resources are also invested to reduce its size. These problems can be addressed by sparsification of an over-complete model, which removes redundant parameters or connections by pruning them away after training or encouraging them to become zero during training. In general, however, these approaches are not fully differentiable and interrupt an end-to-end training process with the stochastic gradient descent in that they require either a parameter selection or a soft-thresholding step. In this paper, we propose a fully differentiable sparsification method for deep neural networks, which allows parameters to be exactly zero during training, and thus can learn the sparsified structure and the weights of networks simultaneously using the stochastic gradient descent. We apply the proposed method to various popular models in order to show its effectiveness.

Boosting is one of the most successful ideas in machine learning. The most well-accepted explanations for the low generalization error of boosting algorithms such as AdaBoost stem from margin theory. The study of margins in the context of boosting algorithms was initiated by Schapire, Freund, Bartlett and Lee (1998) and has inspired numerous boosting algorithms and generalization bounds. To date, the strongest known generalization (upper bound) is the $k$th margin bound of Gao and Zhou (2013). Despite the numerous generalization upper bounds that have been proved over the last two decades, nothing is known about the tightness of these bounds. In this paper, we give the first margin-based lower bounds on the generalization error of boosted classifiers. Our lower bounds nearly match the $k$th margin bound and thus almost settle the generalization performance of boosted classifiers in terms of margins.

In classification models fairness can be ensured by solving a constrained optimization problem. We focus on fairness constraints like Disparate Impact, Demographic Parity, and Equalized Odds, which are non-decomposable and non-convex. Researchers define convex surrogates of the constraints and then apply convex optimization frameworks to obtain fair classifiers. Surrogates serve only as an upper bound to the actual constraints, and convexifying fairness constraints might be challenging.

We propose a neural network-based framework, emph{FNNC}, to achieve fairness while maintaining high accuracy in classification. The above fairness constraints are included in the loss using Lagrangian multipliers. We prove bounds on generalization errors for the constrained losses which asymptotically go to zero. The network is optimized using two-step mini-batch stochastic gradient descent. Our experiments show that FNNC performs as good as the state of the art, if not better. The experimental evidence supplements our theoretical guarantees. In summary, we have an automated solution to achieve fairness in classification, which is easily extendable to many fairness constraints.

When the response mechanism is believed to be not missing at random (NMAR), a valid analysis requires stronger assumptions on the response mechanism than standard statistical methods would otherwise require. Semiparametric estimators have been developed under the model assumptions on the response mechanism. In this paper, a new statistical test is proposed to guarantee model identifiability without using any instrumental variable. Furthermore, we develop optimal semiparametric estimation for parameters such as the population mean. Specifically, we propose two semiparametric optimal estimators that do not require any model assumptions other than the response mechanism. Asymptotic properties of the proposed estimators are discussed. An extensive simulation study is presented to compare with some existing methods. We present an application of our method using Korean Labor and Income Panel Survey data.

Given a multivariate data set, sparse principal component analysis (SPCA) aims to extract several linear combinations of the variables that together explain the variance in the data as much as possible, while controlling the number of nonzero loadings in these combinations. In this paper we consider 8 different optimization formulations for computing a single sparse loading vector; these are obtained by combining the following factors: we employ two norms for measuring variance (L2, L1) and two sparsity-inducing norms (L0, L1), which are used in two different ways (constraint, penalty). Three of our formulations, notably the one with L0 constraint and L1 variance, have not been considered in the literature. We give a unifying reformulation which we propose to solve via a natural alternating maximization (AM) method. We show the the AM method is nontrivially equivalent to GPower (Journ'{e}e et al; JMLR 11:517--553, 2010) for all our formulations. Besides this, we provide 24 efficient parallel SPCA implementations: 3 codes (multi-core, GPU and cluster) for each of the 8 problems. Parallelism in the methods is aimed at i) speeding up computations (our GPU code can be 100 times faster than an efficient serial code written in C++), ii) obtaining solutions explaining more variance and iii) dealing with big data problems (our cluster code is able to solve a 357 GB problem in about a minute).

Increasing number of sectors which affect human lives, are using Machine Learning (ML) tools. Hence the need for understanding their working mechanism and evaluating their fairness in decision-making, are becoming paramount, ushering in the era of Explainable AI (XAI). In this contribution we introduced a few intrinsically interpretable models which are also capable of dealing with missing values, in addition to extracting knowledge from the dataset and about the problem. These models are also capable of visualisation of the classifier and decision boundaries: they are the angle based variants of Learning Vector Quantization. We have demonstrated the algorithms on a synthetic dataset and a real-world one (heart disease dataset from the UCI repository). The newly developed classifiers helped in investigating the complexities of the UCI dataset as a multiclass problem. The performance of the developed classifiers were comparable to those reported in literature for this dataset, with additional value of interpretability, when the dataset was treated as a binary class problem.

The $p$-tensor Curie-Weiss model is a two-parameter discrete exponential family for modeling dependent binary data, where the sufficient statistic has a linear term and a term with degree $p geq 2$. This is a special case of the tensor Ising model and the natural generalization of the matrix Curie-Weiss model, which provides a convenient mathematical abstraction for capturing, not just pairwise, but higher-order dependencies. In this paper we provide a complete description of the limiting properties of the maximum likelihood (ML) estimates of the natural parameters, given a single sample from the $p$-tensor Curie-Weiss model, for $p geq 3$, complementing the well-known results in the matrix ($p=2$) case (Comets and Gidas (1991)). Our results unearth various new phase transitions and surprising limit theorems, such as the existence of a 'critical' curve in the parameter space, where the limiting distribution of the ML estimates is a mixture with both continuous and discrete components. The number of mixture components is either two or three, depending on, among other things, the sign of one of the parameters and the parity of $p$. Another interesting revelation is the existence of certain 'special' points in the parameter space where the ML estimates exhibit a superefficiency phenomenon, converging to a non-Gaussian limiting distribution at rate $N^{frac{3}{4}}$. We discuss how these results can be used to construct confidence intervals for the model parameters and, as a byproduct of our analysis, obtain limit theorems for the sample mean, which provide key insights into the statistical properties of the model.

In Canada, financial advisors and dealers by provincial securities commissions, and those self-regulatory organizations charged with direct regulation over investment dealers and mutual fund dealers, respectively to collect and maintain Know Your Client (KYC) information, such as their age or risk tolerance, for investor accounts. With this information, investors, under their advisor's guidance, make decisions on their investments which are presumed to be beneficial to their investment goals. Our unique dataset is provided by a financial investment dealer with over 50,000 accounts for over 23,000 clients. We use a modified behavioural finance recency, frequency, monetary model for engineering features that quantify investor behaviours, and machine learning clustering algorithms to find groups of investors that behave similarly. We show that the KYC information collected does not explain client behaviours, whereas trade and transaction frequency and volume are most informative. We believe the results shown herein encourage financial regulators and advisors to use more advanced metrics to better understand and predict investor behaviours.

We introduce an optimized physics-informed neural network (PINN) trained to solve the problem of identifying and characterizing a surface breaking crack in a metal plate. PINNs are neural networks that can combine data and physics in the learning process by adding the residuals of a system of Partial Differential Equations to the loss function. Our PINN is supervised with realistic ultrasonic surface acoustic wave data acquired at a frequency of 5 MHz. The ultrasonic surface wave data is represented as a surface deformation on the top surface of a metal plate, measured by using the method of laser vibrometry. The PINN is physically informed by the acoustic wave equation and its convergence is sped up using adaptive activation functions. The adaptive activation function uses a scalable hyperparameter in the activation function, which is optimized to achieve best performance of the network as it changes dynamically the topology of the loss function involved in the optimization process. The usage of adaptive activation function significantly improves the convergence, notably observed in the current study. We use PINNs to estimate the speed of sound of the metal plate, which we do with an error of 1\%, and then, by allowing the speed of sound to be space dependent, we identify and characterize the crack as the positions where the speed of sound has decreased. Our study also shows the effect of sub-sampling of the data on the sensitivity of sound speed estimates. More broadly, the resulting model shows a promising deep neural network model for ill-posed inverse problems.

This paper studies a service system in which arriving customers are provided with information about the delay they will experience. Based on this information they decide to wait for service or to leave the system. The main objective is to estimate the customers' patience-level distribution and the corresponding potential arrival rate, using knowledge of the actual workload process only. We cast the system as a queueing model, so as to evaluate the corresponding likelihood function. Estimating the unknown parameters relying on a maximum likelihood procedure, we prove strong consistency and derive the asymptotic distribution of the estimation error. Several applications and extensions of the method are discussed. In particular, we indicate how our method generalizes to a multi-server setting. The performance of our approach is assessed through a series of numerical experiments. By fitting parameters of hyperexponential and generalized-hyperexponential distributions our method provides a robust estimation framework for any continuous patience-level distribution.

As an important type of reinforcement learning algorithms, actor-critic (AC) and natural actor-critic (NAC) algorithms are often executed in two ways for finding optimal policies. In the first nested-loop design, actor's one update of policy is followed by an entire loop of critic's updates of the value function, and the finite-sample analysis of such AC and NAC algorithms have been recently well established. The second two time-scale design, in which actor and critic update simultaneously but with different learning rates, has much fewer tuning parameters than the nested-loop design and is hence substantially easier to implement. Although two time-scale AC and NAC have been shown to converge in the literature, the finite-sample convergence rate has not been established. In this paper, we provide the first such non-asymptotic convergence rate for two time-scale AC and NAC under Markovian sampling and with actor having general policy class approximation. We show that two time-scale AC requires the overall sample complexity at the order of $mathcal{O}(epsilon^{-2.5}log^3(epsilon^{-1}))$ to attain an $epsilon$-accurate stationary point, and two time-scale NAC requires the overall sample complexity at the order of $mathcal{O}(epsilon^{-4}log^2(epsilon^{-1}))$ to attain an $epsilon$-accurate global optimal point. We develop novel techniques for bounding the bias error of the actor due to dynamically changing Markovian sampling and for analyzing the convergence rate of the linear critic with dynamically changing base functions and transition kernel.

In the field of numerical weather prediction (NWP), the probabilistic distribution of the future state of the atmosphere is sampled with Monte-Carlo-like simulations, called ensembles. These ensembles have deficiencies (such as conditional biases) that can be corrected thanks to statistical post-processing methods. Several ensembles exist and may be corrected with different statistiscal methods. A further step is to combine these raw or post-processed ensembles. The theory of prediction with expert advice allows us to build combination algorithms with theoretical guarantees on the forecast performance. This article adapts this theory to the case of probabilistic forecasts issued as step-wise cumulative distribution functions (CDF). The theory is applied to wind speed forecasting, by combining several raw or post-processed ensembles, considered as CDFs. The second goal of this study is to explore the use of two forecast performance criteria: the Continous ranked probability score (CRPS) and the Jolliffe-Primo test. Comparing the results obtained with both criteria leads to reconsidering the usual way to build skillful probabilistic forecasts, based on the minimization of the CRPS. Minimizing the CRPS does not necessarily produce reliable forecasts according to the Jolliffe-Primo test. The Jolliffe-Primo test generally selects reliable forecasts, but could lead to issuing suboptimal forecasts in terms of CRPS. It is proposed to use both criterion to achieve reliable and skillful probabilistic forecasts.

This paper deals with robust marginal estimation under a general regression model when missing data occur in the response and also in some of covariates. The target is a marginal location parameter which is given through an $M-$functional. To obtain robust Fisher--consistent estimators, properly defined marginal distribution function estimators are considered. These estimators avoid the bias due to missing values by assuming a missing at random condition. Three methods are considered to estimate the marginal distribution function which allows to obtain the $M-$location of interest: the well-known inverse probability weighting, a convolution--based method that makes use of the regression model and an augmented inverse probability weighting procedure that prevents against misspecification. The robust proposed estimators and the classical ones are compared through a numerical study under different missing models including clean and contaminated samples. We illustrate the estimators behaviour under a nonlinear model. A real data set is also analysed.

Text summarization refers to the process that generates a shorter form of text from the source document preserving salient information. Recently, many models for text summarization have been proposed. Most of those models were evaluated using recall-oriented understudy for gisting evaluation (ROUGE) scores. However, as ROUGE scores are computed based on n-gram overlap, they do not reflect semantic meaning correspondences between generated and reference summaries. Because Korean is an agglutinative language that combines various morphemes into a word that express several meanings, ROUGE is not suitable for Korean summarization. In this paper, we propose evaluation metrics that reflect semantic meanings of a reference summary and the original document, Reference and Document Aware Semantic Score (RDASS). We then propose a method for improving the correlation of the metrics with human judgment. Evaluation results show that the correlation with human judgment is significantly higher for our evaluation metrics than for ROUGE scores.

The ability of intelligent agents to learn and remember multiple tasks sequentially is crucial to achieving artificial general intelligence. Many continual learning (CL) methods have been proposed to overcome catastrophic forgetting. Catastrophic forgetting notoriously impedes the sequential learning of neural networks as the data of previous tasks are unavailable. In this paper we focus on class incremental learning, a challenging CL scenario, in which classes of each task are disjoint and task identity is unknown during test. For this scenario, generative replay is an effective strategy which generates and replays pseudo data for previous tasks to alleviate catastrophic forgetting. However, it is not trivial to learn a generative model continually for relatively complex data. Based on recently proposed orthogonal weight modification (OWM) algorithm which can keep previously learned input-output mappings invariant approximately when learning new tasks, we propose to directly generate and replay feature. Empirical results on image and text datasets show our method can improve OWM consistently by a significant margin while conventional generative replay always results in a negative effect. Our method also beats a state-of-the-art generative replay method and is competitive with a strong baseline based on real data storage.

Harnessing data to discover the underlying governing laws or equations that describe the behavior of complex physical systems can significantly advance our modeling, simulation and understanding of such systems in various science and engineering disciplines. Recent advances in sparse identification show encouraging success in distilling closed-form governing equations from data for a wide range of nonlinear dynamical systems. However, the fundamental bottleneck of this approach lies in the robustness and scalability with respect to data scarcity and noise. This work introduces a novel physics-informed deep learning framework to discover governing partial differential equations (PDEs) from scarce and noisy data for nonlinear spatiotemporal systems. In particular, this approach seamlessly integrates the strengths of deep neural networks for rich representation learning, automatic differentiation and sparse regression to approximate the solution of system variables, compute essential derivatives, as well as identify the key derivative terms and parameters that form the structure and explicit expression of the PDEs. The efficacy and robustness of this method are demonstrated on discovering a variety of PDE systems with different levels of data scarcity and noise. The resulting computational framework shows the potential for closed-form model discovery in practical applications where large and accurate datasets are intractable to capture.

In the variational relevance vector machine, the gamma distribution is representative as a hyperprior over the noise precision of automatic relevance determination prior. Instead of the gamma hyperprior, we propose to use the inverse gamma hyperprior with a shape parameter close to zero and a scale parameter not necessary close to zero. This hyperprior is associated with the concept of a weakly informative prior. The effect of this hyperprior is investigated through regression to non-homogeneous data. Because it is difficult to capture the structure of such data with a single kernel function, we apply the multiple kernel method, in which multiple kernel functions with different widths are arranged for input data. We confirm that the degrees of freedom in a model is controlled by adjusting the scale parameter and keeping the shape parameter close to zero. A candidate for selecting the scale parameter is the predictive information criterion. However the estimated model using this criterion seems to cause over-fitting. This is because the multiple kernel method makes the model a situation where the dimension of the model is larger than the data size. To select an appropriate scale parameter even in such a situation, we also propose an extended prediction information criterion. It is confirmed that a multiple kernel relevance vector regression model with good predictive accuracy can be obtained by selecting the scale parameter minimizing extended prediction information criterion.

We present SmartExchange, an algorithm-hardware co-design framework to trade higher-cost memory storage/access for lower-cost computation, for energy-efficient inference of deep neural networks (DNNs). We develop a novel algorithm to enforce a specially favorable DNN weight structure, where each layerwise weight matrix can be stored as the product of a small basis matrix and a large sparse coefficient matrix whose non-zero elements are all power-of-2. To our best knowledge, this algorithm is the first formulation that integrates three mainstream model compression ideas: sparsification or pruning, decomposition, and quantization, into one unified framework. The resulting sparse and readily-quantized DNN thus enjoys greatly reduced energy consumption in data movement as well as weight storage. On top of that, we further design a dedicated accelerator to fully utilize the SmartExchange-enforced weights to improve both energy efficiency and latency performance. Extensive experiments show that 1) on the algorithm level, SmartExchange outperforms state-of-the-art compression techniques, including merely sparsification or pruning, decomposition, and quantization, in various ablation studies based on nine DNN models and four datasets; and 2) on the hardware level, the proposed SmartExchange based accelerator can improve the energy efficiency by up to 6.7$ imes$ and the speedup by up to 19.2$ imes$ over four state-of-the-art DNN accelerators, when benchmarked on seven DNN models (including four standard DNNs, two compact DNN models, and one segmentation model) and three datasets.

Graph Neural Networks (GNNs) are powerful and flexible neural networks that use the naturally sparse connectivity information of the data. GNNs represent this connectivity as sparse matrices, which have lower arithmetic intensity and thus higher communication costs compared to dense matrices, making GNNs harder to scale to high concurrencies than convolutional or fully-connected neural networks.

We present a family of parallel algorithms for training GNNs. These algorithms are based on their counterparts in dense and sparse linear algebra, but they had not been previously applied to GNN training. We show that they can asymptotically reduce communication compared to existing parallel GNN training methods. We implement a promising and practical version that is based on 2D sparse-dense matrix multiplication using torch.distributed. Our implementation parallelizes over GPU-equipped clusters. We train GNNs on up to a hundred GPUs on datasets that include a protein network with over a billion edges.

Motion synthesis in a dynamic environment has been a long-standing problem for character animation. Methods using motion capture data tend to scale poorly in complex environments because of their larger capturing and labeling requirement. Physics-based controllers are effective in this regard, albeit less controllable. In this paper, we present CARL, a quadruped agent that can be controlled with high-level directives and react naturally to dynamic environments. Starting with an agent that can imitate individual animation clips, we use Generative Adversarial Networks to adapt high-level controls, such as speed and heading, to action distributions that correspond to the original animations. Further fine-tuning through the deep reinforcement learning enables the agent to recover from unseen external perturbations while producing smooth transitions. It then becomes straightforward to create autonomous agents in dynamic environments by adding navigation modules over the entire process. We evaluate our approach by measuring the agent's ability to follow user control and provide a visual analysis of the generated motion to show its effectiveness.

The notion of incremental learning is to train an ANN algorithm in stages, as and when newer training data arrives. Incremental learning is becoming widespread in recent times with the advent of deep learning. Noise in the training data reduces the accuracy of the algorithm. In this paper, we make an empirical study of the effect of noise in the training phase. We numerically show that the accuracy of the algorithm is dependent more on the location of the error than the percentage of error. Using Perceptron, Feed Forward Neural Network and Radial Basis Function Neural Network, we show that for the same percentage of error, the accuracy of the algorithm significantly varies with the location of error. Furthermore, our results show that the dependence of the accuracy with the location of error is independent of the algorithm. However, the slope of the degradation curve decreases with more sophisticated algorithms

Restricted Boltzmann Machine (RBM) is an energy based, undirected graphical model. It is commonly used for unsupervised and supervised machine learning. Typically, RBM is trained using contrastive divergence (CD). However, training with CD is slow and does not estimate exact gradient of log-likelihood cost function. In this work, the model expectation of gradient learning for RBM has been calculated using a quantum annealer (D-Wave 2000Q), which is much faster than Markov chain Monte Carlo (MCMC) used in CD. Training and classification results are compared with CD. The classification accuracy results indicate similar performance of both methods. Image reconstruction as well as log-likelihood calculations are used to compare the performance of quantum and classical algorithms for RBM training. It is shown that the samples obtained from quantum annealer can be used to train a RBM on a 64-bit `bars and stripes' data set with classification performance similar to a RBM trained with CD. Though training based on CD showed improved learning performance, training using a quantum annealer eliminates computationally expensive MCMC steps of CD.

This paper revisits the problem of computing empirical cumulative distribution functions (ECDF) efficiently on large, multivariate datasets. Computing an ECDF at one evaluation point requires $mathcal{O}(N)$ operations on a dataset composed of $N$ data points. Therefore, a direct evaluation of ECDFs at $N$ evaluation points requires a quadratic $mathcal{O}(N^2)$ operations, which is prohibitive for large-scale problems. Two fast and exact methods are proposed and compared. The first one is based on fast summation in lexicographical order, with a $mathcal{O}(N{log}N)$ complexity and requires the evaluation points to lie on a regular grid. The second one is based on the divide-and-conquer principle, with a $mathcal{O}(Nlog(N)^{(d-1){vee}1})$ complexity and requires the evaluation points to coincide with the input points. The two fast algorithms are described and detailed in the general $d$-dimensional case, and numerical experiments validate their speed and accuracy. Secondly, the paper establishes a direct connection between cumulative distribution functions and kernel density estimation (KDE) for a large class of kernels. This connection paves the way for fast exact algorithms for multivariate kernel density estimation and kernel regression. Numerical tests with the Laplacian kernel validate the speed and accuracy of the proposed algorithms. A broad range of large-scale multivariate density estimation, cumulative distribution estimation, survival function estimation and regression problems can benefit from the proposed numerical methods.

Reducing domain divergence is a key step in transfer learning problems. Existing works focus on the minimization of global domain divergence. However, two domains may consist of several shared subdomains, and differ from each other in each subdomain. In this paper, we take the local divergence of subdomains into account in transfer. Specifically, we propose to use low-dimensional manifold to represent subdomain, and align the local data distribution discrepancy in each manifold across domains. A Manifold Maximum Mean Discrepancy (M3D) is developed to measure the local distribution discrepancy in each manifold. We then propose a general framework, called Transfer with Manifolds Discrepancy Alignment (TMDA), to couple the discovery of data manifolds with the minimization of M3D. We instantiate TMDA in the subspace learning case considering both the linear and nonlinear mappings. We also instantiate TMDA in the deep learning framework. Extensive experimental studies demonstrate that TMDA is a promising method for various transfer learning tasks.

This paper proposes a logistic undirected network formation model which allows for assortative matching on observed individual characteristics and the presence of edge-wise fixed effects. We model the coefficients of observed characteristics to have a latent community structure and the edge-wise fixed effects to be of low rank. We propose a multi-step estimation procedure involving nuclear norm regularization, sample splitting, iterative logistic regression and spectral clustering to detect the latent communities. We show that the latent communities can be exactly recovered when the expected degree of the network is of order log n or higher, where n is the number of nodes in the network. The finite sample performance of the new estimation and inference methods is illustrated through both simulated and real datasets.

The large volumes of Sentinel-1 data produced over Europe are being used to develop pan-national ground motion services. However, simple analysis techniques like thresholding cannot detect and classify complex deformation signals reliably making providing usable information to a broad range of non-expert stakeholders a challenge. Here we explore the applicability of deep learning approaches by adapting a pre-trained convolutional neural network (CNN) to detect deformation in a national-scale velocity field. For our proof-of-concept, we focus on the UK where previously identified deformation is associated with coal-mining, ground water withdrawal, landslides and tunnelling. The sparsity of measurement points and the presence of spike noise make this a challenging application for deep learning networks, which involve calculations of the spatial convolution between images. Moreover, insufficient ground truth data exists to construct a balanced training data set, and the deformation signals are slower and more localised than in previous applications. We propose three enhancement methods to tackle these problems: i) spatial interpolation with modified matrix completion, ii) a synthetic training dataset based on the characteristics of real UK velocity map, and iii) enhanced over-wrapping techniques. Using velocity maps spanning 2015-2019, our framework detects several areas of coal mining subsidence, uplift due to dewatering, slate quarries, landslides and tunnel engineering works. The results demonstrate the potential applicability of the proposed framework to the development of automated ground motion analysis systems.

Uncertainties in a structure is inevitable, which generally lead to variation in dynamic response predictions. For a complex structure, brute force Monte Carlo simulation for response variation analysis is infeasible since one single run may already be computationally costly. Data driven meta-modeling approaches have thus been explored to facilitate efficient emulation and statistical inference. The performance of a meta-model hinges upon both the quality and quantity of training dataset. In actual practice, however, high-fidelity data acquired from high-dimensional finite element simulation or experiment are generally scarce, which poses significant challenge to meta-model establishment. In this research, we take advantage of the multi-level response prediction opportunity in structural dynamic analysis, i.e., acquiring rapidly a large amount of low-fidelity data from reduced-order modeling, and acquiring accurately a small amount of high-fidelity data from full-scale finite element analysis. Specifically, we formulate a composite neural network fusion approach that can fully utilize the multi-level, heterogeneous datasets obtained. It implicitly identifies the correlation of the low- and high-fidelity datasets, which yields improved accuracy when compared with the state-of-the-art. Comprehensive investigations using frequency response variation characterization as case example are carried out to demonstrate the performance.

Online multiple kernel learning (OMKL) has provided an attractive performance in nonlinear function learning tasks. Leveraging a random feature approximation, the major drawback of OMKL, known as the curse of dimensionality, has been recently alleviated. In this paper, we introduce a new research problem, termed (stream-based) active multiple kernel learning (AMKL), in which a learner is allowed to label selected data from an oracle according to a selection criterion. This is necessary in many real-world applications as acquiring true labels is costly or time-consuming. We prove that AMKL achieves an optimal sublinear regret, implying that the proposed selection criterion indeed avoids unuseful label-requests. Furthermore, we propose AMKL with an adaptive kernel selection (AMKL-AKS) in which irrelevant kernels can be excluded from a kernel dictionary 'on the fly'. This approach can improve the efficiency of active learning as well as the accuracy of a function approximation. Via numerical tests with various real datasets, it is demonstrated that AMKL-AKS yields a similar or better performance than the best-known OMKL, with a smaller number of labeled data.

We develop a general framework for data-driven approximation of input-output maps between infinite-dimensional spaces. The proposed approach is motivated by the recent successes of neural networks and deep learning, in combination with ideas from model reduction. This combination results in a neural network approximation which, in principle, is defined on infinite-dimensional spaces and, in practice, is robust to the dimension of finite-dimensional approximations of these spaces required for computation. For a class of input-output maps, and suitably chosen probability measures on the inputs, we prove convergence of the proposed approximation methodology. Numerically we demonstrate the effectiveness of the method on a class of parametric elliptic PDE problems, showing convergence and robustness of the approximation scheme with respect to the size of the discretization, and compare our method with existing algorithms from the literature.

I study the minimax-optimal design for a two-arm controlled experiment where conditional mean outcomes may vary in a given set. When this set is permutation symmetric, the optimal design is complete randomization, and using a single partition (i.e., the design that only randomizes the treatment labels for each side of the partition) has minimax risk larger by a factor of $n-1$. More generally, the optimal design is shown to be the mixed-strategy optimal design (MSOD) of Kallus (2018). Notably, even when the set of conditional mean outcomes has structure (i.e., is not permutation symmetric), being minimax-optimal for variance still requires randomization beyond a single partition. Nonetheless, since this targets precision, it may still not ensure sufficient uniformity in randomization to enable randomization (i.e., design-based) inference by Fisher's exact test to appropriately detect violations of null. I therefore propose the inference-constrained MSOD, which is minimax-optimal among all designs subject to such uniformity constraints. On the way, I discuss Johansson et al. (2020) who recently compared rerandomization of Morgan and Rubin (2012) and the pure-strategy optimal design (PSOD) of Kallus (2018). I point out some errors therein and set straight that randomization is minimax-optimal and that the "no free lunch" theorem and example in Kallus (2018) are correct.

Current explanation techniques towards a transparent Convolutional Neural Network (CNN) mainly focuses on building connections between the human-understandable input features with models' prediction, overlooking an alternative representation of the input, the frequency components decomposition. In this work, we present an analysis of the connection between the distribution of frequency components in the input dataset and the reasoning process the model learns from the data. We further provide quantification analysis about the contribution of different frequency components toward the model's prediction. We show that the vulnerability of the model against tiny distortions is a result of the model is relying on the high-frequency features, the target features of the adversarial (black and white-box) attackers, to make the prediction. We further show that if the model develops stronger association between the low-frequency component with true labels, the model is more robust, which is the explanation of why adversarially trained models are more robust against tiny distortions.