Spring 2020

February 18, 2020

On the Statistical Complexity of Reinforcement Learning

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

Guessing Random Additive Noise Decoding (GRAND)

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

Are All Features Created Equal?

Speaker: Aleksander Mądry (MIT)

Event Recording:
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? In...

April 28, 2020

Revisiting Exploration versus Exploitation: Adaptive Control and Multi-Armed Bandits

Speaker: P.R. Kumar (Texas A&M University)

Event Recording:
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

Network Independence in Distributed Convex Optimization 

Speaker: Alexander Olshevsky (Boston University)

Event Recording:
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...