English

Nesterov smoothing for sampling without smoothness

Computation 2023-07-25 v3

Abstract

We study the problem of sampling from a target distribution in Rd\mathbb{R}^d whose potential is not smooth. Compared with the sampling problem with smooth potentials, this problem is much less well-understood due to the lack of smoothness. In this paper, we propose a novel sampling algorithm for a class of non-smooth potentials by first approximating them by smooth potentials using a technique that is akin to Nesterov smoothing. We then utilize sampling algorithms on the smooth potentials to generate approximate samples from the original non-smooth potentials. We select an appropriate smoothing intensity to ensure that the distance between the smoothed and un-smoothed distributions is minimal, thereby guaranteeing the algorithm's accuracy. Hence we obtain non-asymptotic convergence results based on existing analysis of smooth sampling. We verify our convergence result on a synthetic example and apply our method to improve the worst-case performance of Bayesian inference on a real-world example.

Keywords

Cite

@article{arxiv.2208.07459,
  title  = {Nesterov smoothing for sampling without smoothness},
  author = {Jiaojiao Fan and Bo Yuan and Jiaming Liang and Yongxin Chen},
  journal= {arXiv preprint arXiv:2208.07459},
  year   = {2023}
}
R2 v1 2026-06-25T01:43:37.954Z