Nesterov smoothing for sampling without smoothness
Abstract
We study the problem of sampling from a target distribution in 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.
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}
}