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
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.