Statistical estimation of ergodic Markov chain kernel over discrete state space

DOI10.3150/20-BEJ1248MaRDI QIDQ2214258zbMATH OpenOpenAlexWikidataFDO

Authors Geoffrey Wolfer, Aryeh Kontorovich

Publication date 7 December 2020

Published in Bernoulli (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1809.05014, https://projecteuclid.org/euclid.bj/1605841254

zbMATH Keywords

discrete state spaceergodic Markov chainminimax theory

Mathematics Subject Classification ID

Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Minimax procedures in statistical decision theory (62C20) Markov processes: estimation; hidden Markov models (62M05)

Abstract: We investigate the statistical complexity of estimating the parameters of a discrete-state Markov chain kernel from a single long sequence of state observations. In the finite case, we characterize (modulo logarithmic factors) the minimax sample complexity of estimation with respect to the operator infinity norm, while in the countably infinite case, we analyze the problem with respect to a natural entry-wise norm derived from total variation. We show that in both cases, the sample complexity is governed by the mixing properties of the unknown chain, for which, in the finite-state case, there are known finite-sample estimators with fully empirical confidence intervals.

Recommendations

• Kernel estimation for stationary density of Markov chains with general state space
• Estimation of the Entropy Rate of a Countable Markov Chain
• scientific article; zbMATH DE number 4043104
• Kernel estimation for real-valued Markov chains
• Density estimation for Markov chains

Cites work

• _p testing and learning of discrete distributions
• A sharp estimate of the binomial mean absolute deviation with applications
• An elementary derivation of the large deviation rate function for finite state Markov chains
• Combinatorial methods in density estimation
• Concentration inequalities for dependent random variables via the martingale method
• Concentration inequalities for Markov chains by Marton couplings and spectral methods
• Eigenvalue bounds on convergence to stationarity for nonreversible Markov chains, with an application to the exclusion process
• Exact lower bounds for the agnostic probably-approximately-correct (PAC) machine learning model
• Geometric ergodicity and hybrid Markov chains
• scientific article; zbMATH DE number 3907540 (Why is no real title available?)
• scientific article; zbMATH DE number 3514781 (Why is no real title available?)
• Introduction to nonparametric estimation
• Markov chains and mixing times. With a chapter on ``Coupling from the past by James G. Propp and David B. Wilson.
• Matrix Analysis
• Minimax Estimation of Discrete Distributions Under <inline-formula> <tex-math notation="LaTeX">$\ell _{1}$ </tex-math></inline-formula> Loss
• Mixing time estimation in reversible Markov chains from a single sample path
• Neural Network Learning
• On the learnability of discrete distributions
• Statistical Methods in Markov Chains

Cited in

(9)

• Special feature: Statistics for COVID-19 pandemic data
• Mixing time estimation in reversible Markov chains from a single sample path
• A low-rank spectral method for learning Markov models
• scientific article; zbMATH DE number 7625185 (Why is no real title available?)
• Improved estimation of relaxation time in nonreversible Markov chains
• On the \(\alpha\)-lazy version of Markov chains in estimation and testing problems
• Structured matrix learning under arbitrary entrywise dependence and estimation of Markov transition kernel
• Non-asymptotic estimates for Markov transition matrices via spectral gap methods
• Robust estimation of a Markov chain transition matrix from multiple sample paths

This page was built for publication: Statistical estimation of ergodic Markov chain kernel over discrete state space

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2214258)