Recently, there has been a great deal of research attention on understanding the convergence behavior of first-order methods using tools from continuous dynamical systems. The alternating direction method of multipliers (ADMM) is a widely used first-order method for solving optimization problems arising from machine learning and statistics, and the stochastic versions of ADMM plays a key role in many modern large-scale machine learning problems. We introduce a unified algorithmic framework called generalized stochastic ADMM and investigate it via a continuous-time analylsis. We rigorously proved that under some proper scaling, the trajectory of stochastic ADMM weakly converges to the trajectory of the stochastic differential equation with small noise parameters. Our analysis also provides a theoretical explanation on why the relaxation parameter should be chosen between 0 and 2.
6月30日
11:00am - 12:00pm

地点
https://hkust.zoom.us/j/5616960008
讲者/表演者
Dr. Huizhuo YUAN
Peking University
Peking University
主办单位
Department of Mathematics
联系方法
mathseminar@ust.hk
付款详情
对象
Alumni, Faculty and Staff, PG Students, UG Students
语言
英语
其他活动

3月24日
研讨会, 演讲, 讲座
IAS / School of Science Joint Lecture - Pushing the Limit of Nonlinear Vibrational Spectroscopy for Molecular Surfaces/Interfaces Studies
Abstract
Surfaces and interfaces are ubiquitous in Nature. Sum-frequency generation vibrational spectroscopy (SFG-VS) is a powerful surface/interface selective and sub-monolayer sensitive spect...

11月22日
研讨会, 演讲, 讲座
IAS / School of Science Joint Lecture - Leveraging Protein Dynamics Memory with Machine Learning to Advance Drug Design: From Antibiotics to Targeted Protein Degradation
Abstract
Protein dynamics are fundamental to protein function and encode complex biomolecular mechanisms. Although Markov state models have made it possible to capture long-timescale protein co...