Non-asymptotic Error Bounds in $\mathcalW_2$-Distance with Sqrt(d) Dimension Dependence and First Order Convergence for Langevin Monte Carlo beyond Log-Concavity

Bin Yang; Xiaojie Wang

2025 ICML ICML 2025

Non-asymptotic Error Bounds in W_2-Distance with Sqrt(d) Dimension Dependence and First Order Convergence for Langevin Monte Carlo beyond Log-Concavity

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Mathematics & Optimization

Authors

Bin Yang, Xiaojie Wang

Topics

Machine Learning > Optimization & Theory > Optimization Mathematics & Optimization > Optimization > Continuous Optimization Mathematics & Optimization > Optimization > Stochastic Methods

Keywords

langevin monte carlo log-sobolev inequality w2-distance log-smooth conditions superlinear growth uniform-in-time convergence

Download PDF