Finite-length analysis on tail probability for Markov chain and application to simple hypothesis testing

DOI10.1214/16-AAP1216MaRDI QIDQ2013570zbMATHOpenAlexFDO

Authors Shun Watanabe, Masahito Hayashi

Publication date 8 August 2017

Published in The Annals of Applied Probability (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1401.3801

zbMATH Keywords

tail probabilityrelative entropyinformation geometryfinite-length Markov chainsimple hypothesis testingrelative Rényi entropy

Mathematics Subject Classification ID

Parametric hypothesis testing (62F03) Markov processes: hypothesis testing (62M02)

Abstract: Using terminologies of information geometry, we derive upper and lower bounds of the tail probability of the sample mean. Employing these bounds, we obtain upper and lower bounds of the minimum error probability of the 2nd kind of error under the exponential constraint for the error probability of the 1st kind of error in a simple hypothesis testing for a finite-length Markov chain, which yields the Hoeffding type bound. For these derivations, we derive upper and lower bounds of cumulant generating function for Markov chain. As a byproduct, we obtain another simple proof of central limit theorem for Markov chain.

Recommendations

• Large deviations, hypotheses testing, and source coding for finite Markov chains
• Limit theorems and testing hypotheses on Markov chains
• scientific article; zbMATH DE number 4062414
• On the converse theorem in statistical hypothesis testing for Markov chains
• On the estimates of error probabilities of hypothesis testing problem in the case of Markov sample

Cited in

(10)

• Asymptotic properties for Markovian dynamics in quantum theory and general probabilistic theories
• Second-order asymptotics for quantum hypothesis testing in settings beyond i.i.d. -- quantum lattice systems and more
• Information geometry of reversible Markov chains
• Function-specific mixing times and concentration away from equilibrium
• Transport-information inequalities for Markov chains
• Information geometry approach to parameter estimation in Markov chains
• Information geometry approach to parameter estimation in hidden Markov model
• Local equivalence problem in hidden Markov model
• Asymptotic and non-asymptotic analysis for a hidden Markovian process with a quantum hidden system
• Long-term concentration of measure and cut-off

This page was built for publication: Finite-length analysis on tail probability for Markov chain and application to simple hypothesis testing

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2013570)