New upper bounds in the hypothesis testing problem with information constraints

DOI10.1134/S0032946020020027MaRDI QIDQ784381zbMATH OpenOpenAlexFDO

Authors M. V. Burnashev

Publication date 3 August 2020

Published in Problems of Information Transmission (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2009.03149

zbMATH Keywords

hypothesis testingerror probabilitiesinformation constraints

Mathematics Subject Classification ID

Statistical aspects of information-theoretic topics (62B10) Parametric hypothesis testing (62F03) Statistical aspects of big data and data science (62R07) Missing data (62D10) Informational aspects of data analysis and big data (94A16)

Abstract: We consider a hypothesis testing problem where a part of data cannot be observed. Our helper observes the missed data and can send us a limited amount of information about them. What kind of this limited information will allow us to make the best statistical inference? In particular, what is the minimum information sufficient to obtain the same results as if we directly observed all the data? We derive estimates for this minimum information and some other similar results.

Recommendations

• On Some Testing of Hypothesis Problems with Information Constraints
• Hypothesis testing with communication constraints
• scientific article; zbMATH DE number 1421014
• On Some Estimation Problems with Information Constraints
• Successive Refinement for Hypothesis Testing and Lossless One-Helper Problem

Cites work

• scientific article; zbMATH DE number 3316587 (Why is no real title available?)
• Code spectrum and the reliability function: binary symmetric channel
• Exponential-type error probabilities for multiterminal hypothesis testing
• Hypothesis testing with communication constraints
• New upper bounds on error exponents
• New upper bounds on the rate of a code via the Delsarte-MacWilliams inequalities
• On Some Estimation Problems with Information Constraints
• On Some Testing of Hypothesis Problems with Information Constraints
• On lower bounds on the spectrum of a binary code
• On minimax estimation in the presence of side information about remote data
• On the BSC reliability function: expanding the region where it is known exactly
• Sharpening of an upper bound for the reliability function of a binary symmetric channel
• Statistical inference under multiterminal data compression

Cited in

(7)

• scientific article; zbMATH DE number 1421014 (Why is no real title available?)
• On Some Estimation Problems with Information Constraints
• On Some Testing of Hypothesis Problems with Information Constraints
• Hypothesis testing with communication constraints
• Limited information estimation and testing subject to linear constraints
• Hypothesis testing with active information
• Successive Refinement for Hypothesis Testing and Lossless One-Helper Problem

This page was built for publication: New upper bounds in the hypothesis testing problem with information constraints

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q784381)