Covariance estimation using Markov chain Monte Carlo

Yunbum Kook, Matthew S. Zhang
10/22/2024
math.STcs.DScs.LG

No confident code implementation found for this paper. 2 possible matches can be shown below.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 2 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Gaussian Invariant Markov Chain Monte Carlo

80% match2025

Efficient MCMC Sampling with Expensive-to-Compute and Irregular Likelihoods

77% match2025

Accelerated Markov Chain Monte Carlo Using Adaptive Weighting Scheme

77% match2024

Efficient Learning for Entropy-Regularized Markov Decision Processes via Multilevel Monte Carlo

77% match2025

Convergence Bounds for Sequential Monte Carlo on Multimodal Distributions using Soft Decomposition

76% match2024

New affine invariant ensemble samplers and their dimensional scaling

76% match1 repo42025

Cite this paper

@article{kook2024covariance,
  title  = {Covariance estimation using Markov chain Monte Carlo},
  author = {Yunbum Kook and Matthew S. Zhang},
  year   = {2024},
  eprint = {2410.17147},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2410.17147v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2410.17147.svg)](https://codeofpaper.com/paper/2410.17147)

Discussion