February 18, 2020
Speaker: Mengdi Wang (Princeton University)
Recent years have witnessed increasing empirical successes in reinforcement learning (RL). However, many theoretical questions about RL were not well understood. For example, how many observations are necessary and sufficient for learning a...
February 25, 2020
Speaker: Muriel Médard (MIT)
Claude Shannon's 1948 "A Mathematical Theory of Communication" provided the basis for the digital communication revolution. As part of that ground-breaking work, he identified the greatest rate (capacity) at which data can be communicated...
March 31, 2020
Speaker: Aleksander Mądry (MIT)
Our machine learning models have attained impressive accuracy on many benchmark tasks. Yet, these models remain remarkably brittle---small perturbations of natural inputs can completely degrade their performance.
Why is this the case?
April 28, 2020
Speaker: P.R. Kumar (Texas A&M University)
We consider the central problem of exploration versus exploitation that lies at the heart of several dynamic learning problems. We revisit the problem of regret in adaptive control and examine it in the light of recent interest in solving...
May 12, 2020
Speaker: Alexander Olshevsky (Boston University)
Distributed optimization has attracted a lot of attention recently as machine learning methods are increasingly trained in parallel over clusters of nodes. Unfortunately, the performance of many distributed optimization algorithms often...