English

A Proximal Algorithm for Sampling from Non-convex Potentials

Machine Learning 2023-02-21 v2

Abstract

We study sampling problems associated with non-convex potentials that meanwhile lack smoothness. In particular, we consider target distributions that satisfy either logarithmic-Sobolev inequality or Poincar\'e inequality. Rather than smooth, the potentials are assumed to be semi-smooth or the summation of multiple semi-smooth functions. We develop a sampling algorithm that resembles proximal algorithms in optimization for this challenging sampling task. Our algorithm is based on a special case of Gibbs sampling known as the alternating sampling framework (ASF). The key contribution of this work is a practical realization of the ASF based on rejection sampling in the non-convex and semi-smooth setting. This work extends the recent algorithm in \cite{LiaChe21,LiaChe22} for non-smooth/semi-smooth log-concave distribution to the setting with non-convex potentials. In almost all the cases of sampling considered in this work, our proximal sampling algorithm achieves better complexity than all existing methods.

Keywords

Cite

@article{arxiv.2205.10188,
  title  = {A Proximal Algorithm for Sampling from Non-convex Potentials},
  author = {Jiaming Liang and Yongxin Chen},
  journal= {arXiv preprint arXiv:2205.10188},
  year   = {2023}
}

Comments

This paper has been merged into "A Proximal Algorithm for Sampling" arXiv:2202.13975v2