Abstract: In this talk, I will present some recent work done by my research group on understanding the relationship between regularization, perturbations, and stability in online learning. In the first part of the talk, I will explain how FTRL (Follow the Regularized Leader) and FTPL (Follow the Perturbed Leader) algorithms can be viewed as two different ways of stabilizing the notoriously unstable FTL (Follow the Leader) algorithm. In the second part of the talk, I will highlight some emerging connections between stability in online learning and the notion of differential privacy.

(Talk is based on several papers written with the following collaborators: Jacob Abernethy, Young Hun Jung, Baekjin Kim, Chansoo Lee, and Audra McMillan.)

Speaker Bio:
Ambuj Tewari is an associate professor in the Department of Statistics and the Department of EECS (by courtesy) at the University of Michigan, Ann Arbor. He is also affiliated with the Michigan Institute for Data Science (MIDAS). He obtained his PhD under the supervision of Peter Bartlett at the University of California at Berkeley. His research interests lie in machine learning including statistical learning theory, online learning, reinforcement learning and control theory, network analysis, and optimization for machine learning. He collaborates with scientists to seek novel applications of machine learning in mobile health, learning analytics, and computational chemistry. His research has been recognized with paper awards at COLT 2005, COLT 2011, and AISTATS 2015. He received an NSF CAREER award in 2015, a Sloan Research Fellowship in 2017, and an Adobe Data Science Award in 2020

This seminar will be livestreamed via Zoom https://umich.zoom.us/j/94350208889
There will be a virtual reception to follow.