Playlist: 26 videos

Frontiers of Deep Learning

0:47:40

Benign Overfitting in Linear Prediction

Peter Bartlett (UC Berkeley)
https://simons.berkeley.edu/talks/tbd-51
Frontiers of Deep Learning
Visit talk page
0:47:59

Practical Model-based Algorithms for Reinforcement Learning and Imitation Learning, with Theoretical Analyses

Tengyu Ma (Stanford University)
https://simons.berkeley.edu/talks/tbd-55
Frontiers of Deep Learning
Visit talk page
0:46:27

Analyzing Optimization and Generalization in Deep Learning via Trajectories of Gradient Descent

Nadav Cohen (Institute for Advanced Study)
https://simons.berkeley.edu/talks/tbd-66
Frontiers of Deep Learning
Visit talk page
0:49:47

From Classical Statistics to Modern Machine Learning

Mikhail Belkin (The Ohio State University)
https://simons.berkeley.edu/talks/tbd-65
Frontiers of Deep Learning
Visit talk page
0:49:42

Learning and Generalization in Over-parametrized Neural Networks, Going Beyond Kernels

Yuanzhi Li (Stanford University)
https://simons.berkeley.edu/talks/tbd-70
Frontiers of Deep Learning
Visit talk page
0:34:34

Size-free Generalization Bounds for Convolutional Neural Networks

Hanie Sedghi (Google Brain)
https://simons.berkeley.edu/talks/tbd-74
Frontiers of Deep Learning
Visit talk page
0:45:39

On the Foundations of Deep Learning: SGD, Overparametrization, and Generalization

Jason Lee (University of Southern California)
https://simons.berkeley.edu/talks/tbd-50
Frontiers of Deep Learning
Visit talk page
0:41:42

A Primal-dual Analysis of Margin Maximization by Steepest Descent Methods

Matus Telgarsky (University of Illinois, Urbana-Champaign)
https://simons.berkeley.edu/talks/tbd-56
Frontiers of Deep Learning
Visit talk page
0:45:12

Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets

Rong Ge (Duke University)
https://simons.berkeley.edu/talks/tbd-61
Frontiers of Deep Learning
Visit talk page
0:49:38

Training on the Test Set and Other Heresies

Ben Recht (UC Berkeley)
https://simons.berkeley.edu/talks/tbd-63
Frontiers of Deep Learning
Visit talk page