Hoeffding's inequalities for geometrically ergodic Markov chains on general state space
B{\l}a\.zej Miasojedow

TL;DR
This paper derives Hoeffding's inequalities for geometrically ergodic Markov chains on general state spaces, providing bounds on large deviations of averages based on spectral properties.
Contribution
It introduces Hoeffding-type bounds for Markov chains with spectral gaps in $L^2$, extending classical inequalities to more general ergodic processes.
Findings
Bounds depend only on stationary mean, spectral gap, and support of $f$
Applicable to Markov chains with spectral gap in $L^2$
Provides probabilistic deviation bounds for averages along trajectories
Abstract
We consider Markov chain with spectral gap in space. Assume that is a bounded function. Then the probabilities of large deviations of average along trajectory satisfy Hoeffding's-type inequalities. These bounds depend only on the stationary mean, spectral gap and the end-points of support of .
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMarkov Chains and Monte Carlo Methods · Stochastic processes and statistical mechanics · Statistical Methods and Inference
