Sequentiality and Adaptivity Gains in Active Hypothesis Testing

Consider a decision maker who is responsible to collect observations so as to enhance his information in a speedy manner about an underlying phenomena of interest. The policies under which the decision maker selects sensing actions can be categorized based on the following two factors: i) sequential versus non-sequential; ii) adaptive versus non-adaptive. Non-sequential policies collect a fixed number of observation samples and make the final decision afterwards; while under sequential policies, the sample size is not known initially and is determined by the observation outcomes. Under adaptive policies, the decision maker relies on the previous collected samples to select the next sensing action; while under non-adaptive policies, the actions are selected independent of the past observation outcomes. In this paper, performance bounds are provided for the policies in each category. Using these bounds, sequentiality gain and adaptivity gain, i.e., the gains of sequential and adaptive selection of actions are characterized.

[1]  George Atia,et al.  Controlled sensing for hypothesis testing , 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

[2]  M. Iwen.  Group testing strategies for recovery of sparse signals in noise , 2009, 2009 Conference Record of the Forty-Third Asilomar Conference on Signals, Systems and Computers.

[3]  Rajesh Sundaresan,et al.  Active sequential hypothesis testing with application to a visual search problem , 2012, 2012 IEEE International Symposium on Information Theory Proceedings.

[4]  Venkatesh Saligrama,et al.  Non-adaptive probabilistic group testing with noisy measurements: Near-optimal bounds with efficient algorithms , 2011, 2011 49th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[5]  Peter Harremoës,et al.  Rényi Divergence and Kullback-Leibler Divergence , 2012, IEEE Transactions on Information Theory.

[6]  Tara Javidi,et al.  Active Sequential Hypothesis Testing , 2012, ArXiv.

[7]  E. Berlekamp.  Block coding with noiseless feedback , 1964 .

[8]  I. Vajda,et al.  Convex Statistical Distances , 2018, Statistical Inference for Engineers and Data Scientists.

[9]  Neri Merhav,et al.  Universal composite hypothesis testing: A competitive minimax approach , 2002, IEEE Trans. Inf. Theory.

[10]  J. Kiefer,et al.  Asymptotically Optimum Sequential Inference and Design , 1963 .

[11]  G. Lorden.  Nearly-optimal sequential tests for finitely many parameter values , 1977 .

[12]  Evgueni Haroutunian,et al.  Reliability Criteria in Information Theory and in Statistical Hypothesis Testing , 2008, Found. Trends Commun. Inf. Theory.

[13]  V. Bentkus,et al.  An extension of the Hoeffding inequality to unbounded random variables , 2008 .

[14]  Tara Javidi,et al.  Information utility in active sequential hypothesis testing , 2010, 2010 48th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[15]  Baris Nakiboglu.  Exponential bounds on error probability with Feedback , 2011 .

[16]  Urbashi Mitra,et al.  Parametric Methods for Anomaly Detection in Aggregate Traffic , 2011, IEEE/ACM Transactions on Networking.

[17]  G. Lorden,et al.  A Control Problem Arising in the Sequential Design of Experiments , 1986 .

[18]  M. V. Burnašev.  SEQUENTIAL DISCRIMINATION OF HYPOTHESES WITH CONTROL OF OBSERVATIONS , 1980 .

[19]  Venugopal V. Veeravalli,et al.  Multihypothesis sequential probability ratio tests - Part I: Asymptotic optimality , 1999, IEEE Trans. Inf. Theory.

[20]  Colin McDiarmid,et al.  Surveys in Combinatorics, 1989: On the method of bounded differences , 1989 .

[21]  D. Blackwell.  Equivalent Comparisons of Experiments , 1953 .

[22]  Tara Javidi,et al.  Variable-length coding with noiseless feedback and finite messages , 2010, 2010 Conference Record of the Forty Fourth Asilomar Conference on Signals, Systems and Computers.

[23]  Alfred O. Hero,et al.  Sensor Management: Past, Present, and Future , 2011, IEEE Sensors Journal.

[24]  J. Norris.  Appendix: probability and measure , 1997 .

[25]  Ertem Tuncel,et al.  On error exponents in hypothesis testing , 2005, IEEE Transactions on Information Theory.

[26]  Sean P. Meyn,et al.  Universal and Composite Hypothesis Testing via Mismatched Divergence , 2009, IEEE Transactions on Information Theory.

[27]  Masahito Hayashi,et al.  Discrimination of Two Channels by Adaptive Methods and Its Application to Quantum System , 2008, IEEE Transactions on Information Theory.

[28]  D. Meeter,et al.  Sequential Experimental Design Procedures , 1973 .

[29]  Walter T. Federer,et al.  Sequential Design of Experiments , 1967 .

[30]  A. Albert.  The Sequential Design of Experiments for Infinitely Many States of Nature , 1961 .

[31]  Tara Javidi,et al.  Active hypothesis testing: Sequentiality and adaptivity gains , 2012, 2012 46th Annual Conference on Information Sciences and Systems (CISS).

[32]  George Atia,et al.  Controlled Sensing for Multihypothesis Testing , 2012, IEEE Transactions on Automatic Control.

[33]  Robert D. Nowak,et al.  The Geometry of Generalized Binary Search , 2009, IEEE Transactions on Information Theory.

[34]  Ofer Shayevitz,et al.  On Rényi measures and hypothesis testing , 2011, 2011 IEEE International Symposium on Information Theory Proceedings.

[35]  Pravin Varaiya,et al.  Stochastic Systems: Estimation, Identification, and Adaptive Control , 1986 .

[36]  Bernard C. Levy,et al.  Robust Hypothesis Testing With a Relative Entropy Tolerance , 2007, IEEE Transactions on Information Theory.

[37]  J. Wolfowitz,et al.  Optimum Character of the Sequential Probability Ratio Test , 1948 .

[38]  Imre Csiszár,et al.  Information Theory and Statistics: A Tutorial , 2004, Found. Trends Commun. Inf. Theory.

[39]  P. Armitage.  Sequential Analysis with More than Two Alternative Hypotheses, and its Relation to Discriminant Function Analysis , 1950 .

[40]  Tara Javidi,et al.  Performance bounds for active sequential hypothesis testing , 2011, 2011 IEEE International Symposium on Information Theory Proceedings.

[41]  Matthew Malloy,et al.  Sequential analysis in high-dimensional multiple testing and sparse recovery , 2011, 2011 IEEE International Symposium on Information Theory Proceedings.

[42]  Richard E. Blahut,et al.  Hypothesis testing and information theory , 1974, IEEE Trans. Inf. Theory.

[43]  Pradeep Shenoy,et al.  Rational Decision-Making in Inhibitory Control , 2011, Front. Hum. Neurosci..

[44]  R. Keener.  Second Order Efficiency in the Sequential Design of Experiments , 1984 .

[45]  Geoffrey A. Hollinger,et al.  Active Classification: Theory and Application to Underwater Inspection , 2011, ISRR.

[46]  László Györfi,et al.  A note on robust hypothesis testing , 2002, IEEE Trans. Inf. Theory.