An information theoretic analysis of sequential decision-making

First Authors Meik Dörpinghaus
Authors Meik Dörpinghaus, Édgar Roldán, Izaak Neri, Heinrich Meyr, Frank Jülicher
Corresponding Authors
Last Authors Frank Jülicher
Conference Proceedings Volume Title 2017 IEEE International Symposium on Information Theory (ISIT) : 25-30 June 2017
Series Title
Conference Name 2017 IEEE International Symposium on Information Theory, ISIT 2017 : 25-30 June 2017
Conference Location Aachen; Germany
Conference Start Date 0017-06-27
Conference End Date 0017-07-02
Chapter Number
Publisher IEEE
Conference Proceedings Editors Gerhard Kramer
ISBN 978-1-5090-4097-1
First Page 3050
Last Page 3054
Open Access false
Print Publication Date 2017-08-09
Online Publication Date 2017-08-09
Abstract We provide a novel analysis of Wald's sequential probability ratio test based on information theoretic measures for symmetric thresholds, symmetric noise, and equally likely hypotheses. This test is optimal in the sense that it yields the minimum mean decision time. To analyze the decision-making process we consider information densities, which represent the stochastic information content of the observations yielding a stochastic termination time of the test. Based on this, we show that the conditional probability to decide for hypothesis H1 (or the counter-hypothesis H0) given that the test terminates at time instant k is independent of time k. An analogous property has been found for a continuous-time first passage problem with two absorbing boundaries in the contexts of non-equilibrium statistical physics and communication theory. Moreover, we study the evolution of the mutual information between the binary variable to be tested and the output of the Wald test. Notably, we show that the decision time of the Wald test contains no information on which hypothesis is true beyond the decision outcome
Cover Image
Affiliated With Zerial
Selected By
Acknowledged Services
Publication Status Published
Edoc Link
Sfx Link
DOI 10.1109/ISIT.2017.8007090
PubMed ID
WebOfScience Link
Alternative Full Text URL
Display Publisher Download Only false
Visible On MPI-CBG Website true
PDF Downloadable true
Created By thuem
Added Date 2018-03-01
Last Edited By thuem
Last Edited Date 2018-03-01 15:42:44.711
Library ID 7073
Document ID
Entry Complete true
eDoc Compliant true
Include in Edoc Report true
In Pure
Ready for eDoc Export
Author Affiliations Complete false
Project Name
Project URL
Grant ID
Funding Programme
Funding Organisation