Langevin Algorithms in Machine Learning

讲座时间 Datetime: 2023年6月27日，星期二， 10:00-12:00

地点 Venue: 海琴2号A457

报告人 Speaker: 朱凌炯 副教授

单位 Affiliation: Florida State University

主持人Host：蔡春浩 副教授

报告摘要 Abstract:

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 problems with high-dimensional models and stochastic non-convex optimization problems including the challenging problems arising in deep learning. In this talk, we first discuss Langevin algorithms for non-convex optimization, and show that acceleration is possible for momentum-based Langevin algorithms in the context of non-convex optimization. Next, we illustrate the applications of Langevin algorithms in sampling and Bayesian learning via decentralized Langevin algorithms and penalized Langevin algorithms. Finally, we discuss heavy-tailed Langevin dynamics to approximate stochastic gradient algorithms and provide insights in the context of deep learning, as well as related algorithms and phenomena.

报告人简介：

朱凌炯现为佛罗里达州立大学金融数学系副教授，朱凌炯博士毕业于纽约大学克朗索研究所。他的研究主要集中在应用概率，数据科学，管理科学，金融工程。论文发表在Annals of applied probability, Operations Research, International Conference on Machine Learning等顶尖杂志。