CODSLGOCFeb 23, 2023

Efficiently handling constraints with Metropolis-adjusted Langevin algorithm

arXiv:2302.11971v21 citationsh-index: 19
AI Analysis

This addresses a challenge in Markov chain Monte Carlo methods for constrained distributions, but appears incremental as it builds on existing algorithms.

The study tackled the problem of applying the Metropolis-adjusted Langevin algorithm to constrained target distributions, showing it is highly effective with a superior mixing time bound compared to competing algorithms without an accept-reject step.

In this study, we investigate the performance of the Metropolis-adjusted Langevin algorithm in a setting with constraints on the support of the target distribution. We provide a rigorous analysis of the resulting Markov chain, establishing its convergence and deriving an upper bound for its mixing time. Our results demonstrate that the Metropolis-adjusted Langevin algorithm is highly effective in handling this challenging situation: the mixing time bound we obtain is superior to the best known bounds for competing algorithms without an accept-reject step. Our numerical experiments support these theoretical findings, indicating that the Metropolis-adjusted Langevin algorithm shows promising performance when dealing with constraints on the support of the target distribution.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes