摘要：
In recent years, there has been great progress in developing faster algorithms for log-concave sampling. It's natural to ask whether the algorithmic upper bounds are tight. Thus, it's necessary to establish query complexity lower bounds for sampling. 

In this talk, we will introduce some results on query lower bounds for log-concave sampling, based on a recent work by Chewi, Pont, Li, Lu, Narayanan[2023]. We will also introduce a lower bound for sampling algorithms which simulate underdamped Langevin dynamics, based on a work by Cao, Lu, Wang[2019].

论坛简介：该线上论坛是由张志华教授机器学习实验室组织，每两周主办一次（除了公共假期）。论坛每次邀请一位博士生就某个前沿课题做较为系统深入的介绍，主题包括但不限于机器学习、高维统计学、运筹优化和理论计算机科学。