Covariance estimation using Markov chain Monte Carlo

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Kook, Yunbum, Zhang, Matthew S.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910661053775872
author Kook, Yunbum
Zhang, Matthew S.
author_facet Kook, Yunbum
Zhang, Matthew S.
contents We investigate the complexity of covariance matrix estimation for Gibbs distributions based on dependent samples from a Markov chain. We show that when $π$ satisfies a Poincaré inequality and the chain possesses a spectral gap, we can achieve similar sample complexity using MCMC as compared to an estimator constructed using i.i.d. samples, with potentially much better query complexity. As an application of our methods, we show improvements for the query complexity in both constrained and unconstrained settings for concrete instances of MCMC. In particular, we provide guarantees regarding isotropic rounding procedures for sampling uniformly on convex bodies.
format Preprint
id arxiv_https___arxiv_org_abs_2410_17147
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Covariance estimation using Markov chain Monte Carlo
Kook, Yunbum
Zhang, Matthew S.
Statistics Theory
Data Structures and Algorithms
Machine Learning
We investigate the complexity of covariance matrix estimation for Gibbs distributions based on dependent samples from a Markov chain. We show that when $π$ satisfies a Poincaré inequality and the chain possesses a spectral gap, we can achieve similar sample complexity using MCMC as compared to an estimator constructed using i.i.d. samples, with potentially much better query complexity. As an application of our methods, we show improvements for the query complexity in both constrained and unconstrained settings for concrete instances of MCMC. In particular, we provide guarantees regarding isotropic rounding procedures for sampling uniformly on convex bodies.
title Covariance estimation using Markov chain Monte Carlo
topic Statistics Theory
Data Structures and Algorithms
Machine Learning
url https://arxiv.org/abs/2410.17147