Back to Search Start Over

Nesterov smoothing for sampling without smoothness

Authors :
Fan, Jiaojiao
Yuan, Bo
Liang, Jiaming
Chen, Yongxin
Source :
IEEE CDC 2023
Publication Year :
2022

Abstract

We study the problem of sampling from a target distribution in $\mathbb{R}^d$ 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.

Subjects

Subjects :
Statistics - Computation

Details

Database :
arXiv
Journal :
IEEE CDC 2023
Publication Type :
Report
Accession number :
edsarx.2208.07459
Document Type :
Working Paper