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

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=Lmj2bU9MdwM


Duration: 46:27
3,346 views
69

Nadav Cohen (Institute for Advanced Study)
https://simons.berkeley.edu/talks/tbd-66
Frontiers of Deep Learning



Other Videos By Simons Institute for the Theory of Computing


2019-07-16Splitting Gradient Descent for Incremental Learning of Neural Architectures
2019-07-16Mad Max: Affine Spline Insights into Deep Learning
2019-07-16Computation in Very Wide Neural Networks
2019-07-16Training on the Test Set and Other Heresies
2019-07-16Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets
2019-07-16A Primal-dual Analysis of Margin Maximization by Steepest Descent Methods
2019-07-16On the Foundations of Deep Learning: SGD, Overparametrization, and Generalization
2019-07-15Size-free Generalization Bounds for Convolutional Neural Networks
2019-07-15Learning and Generalization in Over-parametrized Neural Networks, Going Beyond Kernels
2019-07-15From Classical Statistics to Modern Machine Learning
2019-07-15Analyzing Optimization and Generalization in Deep Learning via Trajectories of Gradient Descent
2019-07-15Practical Model-based Algorithms for Reinforcement Learning and Imitation Learning, with...
2019-07-15Benign Overfitting in Linear Prediction
2019-07-12Expansion from a Cohomological Viewpoint
2019-07-12Spectral HDX III: Random Walks
2019-07-12Connection Between Codes and HDX Part 2
2019-07-12Connection Between Codes and HDX Part 1
2019-07-11Spectral HDX II: Local to Global
2019-07-11Spectral HDX I
2019-07-11High Dimensional Expanders - Introduction and Motivation
2019-07-10Journalist-in-Residence Talk: The Limits of Fairness


Tags:
Frontiers of Deep Learning
Nadav Cohen
Simons Institute
Theory of Computing
Theory of Computation
Theoretical Computer Science
Computer Science
UC Berkeley