English

A Proximal Algorithm for Sampling from Non-smooth Potentials

Machine Learning 2022-02-11 v2 Optimization and Control

Abstract

In this work, we examine sampling problems with non-smooth potentials. We propose a novel Markov chain Monte Carlo algorithm for sampling from non-smooth potentials. We provide a non-asymptotical analysis of our algorithm and establish a polynomial-time complexity O~(dε1)\tilde {\cal O}(d\varepsilon^{-1}) to obtain ε\varepsilon total variation distance to the target density, better than most existing results under the same assumptions. Our method is based on the proximal bundle method and an alternating sampling framework. This framework requires the so-called restricted Gaussian oracle, which can be viewed as a sampling counterpart of the proximal mapping in convex optimization. One key contribution of this work is a fast algorithm that realizes the restricted Gaussian oracle for any convex non-smooth potential with bounded Lipschitz constant.

Keywords

Cite

@article{arxiv.2110.04597,
  title  = {A Proximal Algorithm for Sampling from Non-smooth Potentials},
  author = {Jiaming Liang and Yongxin Chen},
  journal= {arXiv preprint arXiv:2110.04597},
  year   = {2022}
}

Comments

20 pages