Robust Hypothesis Testing With a Relative Entropy Tolerance

DOI10.1109/TIT.2008.2008128zbMATH Open1367.62018arXiv0707.2926OpenAlexW3099452348MaRDI QIDQ4975705FDOQ4975705

Authors: Bernard C. Levy 

Publication date: 8 August 2017

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Abstract: This paper considers the design of a minimax test for two hypotheses where the actual probability densities of the observations are located in neighborhoods obtained by placing a bound on the relative entropy between actual and nominal densities. The minimax problem admits a saddle point which is characterized. The robust test applies a nonlinear transformation which flattens the nominal likelihood ratio in the vicinity of one. Results are illustrated by considering the transmission of binary data in the presence of additive noise.

Full work available at URL: https://arxiv.org/abs/0707.2926

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Nonparametric hypothesis testing (62G10) Nonparametric robustness (62G35) Measures of information, entropy (94A17)

Cited In (4)

• Adversarially robust sequential hypothesis testing
• Robust hypothesis testing for asymmetric nominal densities under a relative entropy tolerance
• Robust Least-Squares Estimation With a Relative Entropy Constraint
• Frameworks and results in distributionally robust optimization

This page was built for publication: Robust Hypothesis Testing With a Relative Entropy Tolerance

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4975705)