Large-Time Analysis of the Langevin Dynamics for Energies Fulfilling Polyak-{\L}ojasiewicz Conditions
Massimo Fornasier, Lukang Sun, Rachel Ward

TL;DR
This paper analyzes the long-term behavior of Langevin dynamics for objective functions satisfying Polyak-Lojasiewicz conditions, establishing convergence rates and diffusion properties under minimal assumptions.
Contribution
It provides the first systematic analysis of Langevin dynamics under PL conditions in non-integrable Gibbs settings, including exponential convergence and diffusion results.
Findings
Law converges to Gibbs measure in integrable case
Law diffuses in non-integrable case with rate O(1/t)
Exponential contraction toward minimizers under PL condition
Abstract
In this work, we take a step towards understanding overdamped Langevin dynamics for the minimization of a general class of objective functions . We establish well-posedness and regularity of the law of the process through novel a priori estimates, and, very importantly, we characterize the large-time behavior of under truly minimal assumptions on . In the case of integrable Gibbs density, the law converges to the normalized Gibbs measure. In the non-integrable case, we prove that the law diffuses. The rate of convergence is . Under a Polyak-Lojasiewicz (PL) condition on , we also derive sharp exponential contractivity results toward the set of global minimizers. Combining these results we provide the first systematic convergence analysis of Langevin dynamics under PL conditions in non-integrable Gibbs settings: a…
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.
