Gespeichert in:
Bibliographische Detailangaben
1. Verfasser: Nakakita, Shogo
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2601.21717
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910020806901760
author Nakakita, Shogo
author_facet Nakakita, Shogo
contents We establish sample complexity guarantees for estimating the covariance matrix of a strongly log-concave smooth distribution using the unadjusted Langevin algorithm (ULA). We quantitatively compare our complexity estimates on single-chain ULA with embarrassingly parallel ULA and derive that the sample complexity of the single-chain approach is smaller than that of embarrassingly parallel ULA by a logarithmic factor in the dimension and the reciprocal of the prescribed precision, with the difference arising from effective bias reduction through burn-in. The key technical contribution is a concentration bound for the sample covariance matrix around its expectation, derived via a log-Sobolev inequality for the joint distribution of ULA iterates.
format Preprint
id arxiv_https___arxiv_org_abs_2601_21717
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle On sample complexity for covariance estimation via the unadjusted Langevin algorithm
Nakakita, Shogo
Probability
Machine Learning
65C05 (Primary) 60J05, 62F12 (Secondary)
We establish sample complexity guarantees for estimating the covariance matrix of a strongly log-concave smooth distribution using the unadjusted Langevin algorithm (ULA). We quantitatively compare our complexity estimates on single-chain ULA with embarrassingly parallel ULA and derive that the sample complexity of the single-chain approach is smaller than that of embarrassingly parallel ULA by a logarithmic factor in the dimension and the reciprocal of the prescribed precision, with the difference arising from effective bias reduction through burn-in. The key technical contribution is a concentration bound for the sample covariance matrix around its expectation, derived via a log-Sobolev inequality for the joint distribution of ULA iterates.
title On sample complexity for covariance estimation via the unadjusted Langevin algorithm
topic Probability
Machine Learning
65C05 (Primary) 60J05, 62F12 (Secondary)
url https://arxiv.org/abs/2601.21717