CS Research Talk: TIn Search of Better Parallel Optimization Algorithms for Machine Learning

Dr. Blake Woodworth
Inria de Paris
Postdoctoral Researcher

Wednesday, January 26, 2022 | 9:30 a.m. – 10:30 a.m.
Join via Zoom

TIn Search of Better Parallel Optimization Algorithms for Machine Learning

Abstract

A key factor in the recent success of machine learning has been the use of very large models and huge quantities of data. This has raised computational challenges and it demands leveraging distributed optimization algorithms to make training possible. But which parallel algorithms should we use? In this talk, I will identify optimal distributed optimization algorithms in several natural settings, and I will propose directions that may allow us to find new, "better than optimal" methods. I will also highlight some of my other research interests at the intersection of optimization and machine learning, including efforts to understand how highly overparameterized models like deep neural networks manage to generalize so well.

Bio

Blake Woodworth is currently a postdoctoral researcher at Inria, working with Francis Bach. Until September 2021, he was a Ph.D. student in computer science at TTIC advised by Nathan Srebro. He is interested in optimization and learning theory with the goal of developing algorithms that make machine learning easier and more successful. Specific topics of interest include distributed optimization, non-convex optimization, implicit regularization, fairness in machine learning, and adaptive data analysis. His research has been recognized with the Best Student Paper award at COLT 2019 and the Best Paper award at COLT 2021, and his graduate studies were supported by a NSF GRFP award and a Google Research Ph.D. Fellowship.