Abstract: Recent theoretical works on over-parameterized neural nets have focused on two aspects: optimization and generalization. Many existing works…

Abstract Reinforcement learning (RL) has gained popularity in the research community as a model-free and adaptive control paradigm for the...

The talk will cover two complexity-theoretic results from optimization. We will review work on an accelerated algorithm (à la Nesterov)...

How can we design AI to benefit society? In this talk, I will discuss the stakes involved in ensuring that...