Long-time reverse transportation inequalities for non-globally-dissipative Langevin dynamics
Jianfeng Lu, Yuliang Wang

TL;DR
This paper proves a dimension-free, uniform-in-time reverse transportation inequality for Langevin dynamics with non-convex potentials, extending long-time convergence results beyond log-concave cases.
Contribution
It introduces a novel reverse transportation inequality for non-convex Langevin dynamics that remains valid over long times and does not depend on dimension.
Findings
Establishes a uniform-in-time reverse transportation inequality for non-convex Langevin dynamics.
Shows exponential decay of the inequality in the long-time regime.
Extends results from log-concave to non-convex potential settings.
Abstract
We establish a dimension-free, uniform-in-time reverse transportation inequality for Langevin dynamics with non-convex potentials. This inequality controls the R\'enyi divergence of arbitrary order between the process distributions starting from distinct initial points and serves as the dual version of the Harnack inequality. Notably, we prove that this inequality retains exponential decay in the long-time regime, thereby extending existing results for log-concave sampling to the non-convex setting.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMarkov Chains and Monte Carlo Methods · Stochastic processes and statistical mechanics · Random Matrices and Applications
