NeurIPS 2022accept7 citations

Constrained Langevin Algorithms with L-mixing External Random Variables

Yuping Zheng, Andrew Lamperski

Abstract

Langevin algorithms are gradient descent methods augmented with additive noise, and are widely used in Markov Chain Monte Carlo (MCMC) sampling, optimization, and machine learning. In recent years, the non-asymptotic analysis of Langevin algorithms for non-convex learning has been extensively explored. For constrained problems with non-convex losses over a compact convex domain with IID data variables, the projected Langevin algorithm achieves a deviation of $O(T^{-1/4} (\log T)^{1/2})$ from its target distribution \cite{lamperski2021projected} in $1$-Wasserstein distance. In this paper, we obtain a deviation of $O(T^{-1/2} \log T)$ in $1$-Wasserstein distance for non-convex losses with $L$-mixing data variables and polyhedral constraints (which are not necessarily bounded). This improves on the previous bound for constrained problems and matches the best-known bound for unconstrained problems.

Langevin algorithmsL-mixing processesGradient descent methodsNon-convex optimizationNon-asymptotic analysisMarkov Chain Monte Carlo sampling
BibTeX
@inproceedings{
zheng2022constrained,
title={Constrained Langevin Algorithms with L-mixing External Random Variables},
author={Yuping Zheng and Andrew Lamperski},
booktitle={Advances in Neural Information Processing Systems},
editor={Alice H. Oh and Alekh Agarwal and Danielle Belgrave and Kyunghyun Cho},
year={2022},
url={https://openreview.net/forum?id=KxVSnZVuZZ}
}
Constrained Langevin Algorithms with L-mixing External Random Variables · NeurIPS 2022