CMI Seminar: Pan Xu

Nonconvex optimization plays a central role in modern machine learning. How to design data-efficient optimization algorithms that have a low sample complexity while enjoying a fast convergence at the same time remains a pressing and challenging research question. In this talk, I will discuss the sample efficiency of stochastic gradient-based algorithms for solving nonconvex optimization problems. I will first introduce first-order optimization algorithms that achieve improved sample efficiency by using variance reduction techniques. Then I will show that these variance reduction techniques can be used to develop sample-efficient algorithms for policy optimization problems in reinforcement learning.