Title: Understanding Deep Learning via Analyzing Trajectories of Gradient Descent【IIIS-Haihua Frontier Seminar Series】
Speaker: Wei Hu Princeton University
Time: 2019-12-17 14:00-2019-12-17 15:00
Venue: Block D 15th floor, Science & Technology Mansion, Tsinghua Science Park

Abstract:

Deep learning builds upon the mysterious abilities of gradient-based optimization algorithms. Not only can these algorithms often achieve low loss on complicated non-convex training objectives, but the solutions found can also generalize remarkably well on unseen test data. Towards explaining these mysteries, I will present recent results that take into account the trajectories taken by the gradient descent algorithm -- the trajectories turn out to exhibit special properties that enable the successes of optimization and generalization.



Short Bio:

Wei Hu is a PhD student in the Department of Computer Science at Princeton University, advised by Sanjeev Arora. Previously, he obtained his B.E. in Computer Science from Tsinghua University, where he was a member of Yao Class. He has also spent time at research labs of Google and Microsoft. His current research interest is in the theoretical foundation of modern machine learning and optimization.