Sampling under log-concavity and isoperimetry
组织者
演讲者
时间
2023年08月21日 14:30 至 15:00
地点
数学系理科楼A-203
摘要
The primary aim of this report is to introduce the complexity of the task of sampling: given a target probability density π ∝ exp(−V ) on R^d , how expensive is it to generate random variables whose law is close to π in suitable metrics? Since the dawn of the Markov chain Monte Carlo (MCMC) revolution, sampling has been the algorithmic cornerstone of Bayesian inference and scientific computing. How do we design fast samplers, and how can we develop a theory of complexity for this task?