English

Sharp convergence rates for Langevin dynamics in the nonconvex setting

Machine Learning 2020-07-07 v4 Machine Learning Probability Computation

Abstract

We study the problem of sampling from a distribution p(x)exp(U(x))p^*(x) \propto \exp\left(-U(x)\right), where the function UU is LL-smooth everywhere and mm-strongly convex outside a ball of radius RR, but potentially nonconvex inside this ball. We study both overdamped and underdamped Langevin MCMC and establish upper bounds on the number of steps required to obtain a sample from a distribution that is within ϵ\epsilon of pp^* in 11-Wasserstein distance. For the first-order method (overdamped Langevin MCMC), the iteration complexity is O~(ecLR2d/ϵ2)\tilde{\mathcal{O}}\left(e^{cLR^2}d/\epsilon^2\right), where dd is the dimension of the underlying space. For the second-order method (underdamped Langevin MCMC), the iteration complexity is O~(ecLR2d/ϵ)\tilde{\mathcal{O}}\left(e^{cLR^2}\sqrt{d}/\epsilon\right) for an explicit positive constant cc. Surprisingly, the iteration complexity for both these algorithms is only polynomial in the dimension dd and the target accuracy ϵ\epsilon. It is exponential, however, in the problem parameter LR2LR^2, which is a measure of non-log-concavity of the target distribution.

Keywords

Cite

@article{arxiv.1805.01648,
  title  = {Sharp convergence rates for Langevin dynamics in the nonconvex setting},
  author = {Xiang Cheng and Niladri S. Chatterji and Yasin Abbasi-Yadkori and Peter L. Bartlett and Michael I. Jordan},
  journal= {arXiv preprint arXiv:1805.01648},
  year   = {2020}
}

Comments

78 pages, 2 figures

R2 v1 2026-06-23T01:44:56.195Z