AI Chat AI Image Generator AI Video Text to Speech

Non-asymptotic error bounds for scaled underdamped Langevin MCMC

12/06/2019

∙

by Tim Zajic, et al.

∙

∙

Recent works have derived non-asymptotic upper bounds for convergence of underdamped Langevin MCMC. We revisit these bound and consider introducing scaling terms in the underlying underdamped Langevin equation. In particular, we provide conditions under which an appropriate scaling allows to improve the error bounds in terms of the condition number of the underlying density of interest.

page 1

page 2

page 3

page 4

research

∙ 05/23/2019

Estimating Convergence of Markov chains with L-Lag Couplings

Markov chain Monte Carlo (MCMC) methods generate samples that are asympt...

0 Niloy Biswas, et al. ∙

research

∙ 02/03/2012

Minimax Rates of Estimation for Sparse PCA in High Dimensions

We study sparse principal components analysis in the high-dimensional se...

0 Vincent Q. Vu, et al. ∙

research

∙ 05/04/2018

Sharp Convergence Rates for Langevin Dynamics in the Nonconvex Setting

We study the problem of sampling from a distribution where the negative ...

0 Xiang Cheng, et al. ∙

research

∙ 05/15/2019

Stochastic approximation with cone-contractive operators: Sharp ℓ_∞-bounds for Q-learning

Motivated by the study of Q-learning algorithms in reinforcement learnin...

0 Martin J. Wainwright, et al. ∙

research

∙ 02/24/2023

On Stein's lemma in hypotheses testing in general non-asymptotic case

The problem of testing two simple hypotheses in a general probability sp...

0 Marat V. Burnashev, et al. ∙

research

∙ 03/18/2019

Variance reduction for MCMC methods via martingale representations

In this paper we propose an efficient variance reduction approach for MC...

0 D. Belomestny, et al. ∙

research

∙ 01/15/2019

Improved Credit Bounds for the Credit-Based Shaper in Time-Sensitive Networking

In Time Sensitive Networking (TSN), it is important to formally prove pe...

0 Ehsan Mohammadpour, et al. ∙