学术报告（朱凌炯 12.20）

摘要：Langevin algorithms are core Markov Chain Monte Carlo methods for solving machine learning problems. These methods arise in several contexts in machine learning and data science including Bayesian (learning) inference problems with high-dimensional models and stochastic non-convex optimization problems including the challenging problems arising in deep learning. In this talk, we illustrate the applications of Langevin algorithms through three examples: (1) Langevin algorithms for non-convex optimization; (2) Decentralized Langevin algorithms; (3) Constrained sampling via penalized Langevin algorithms.