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

Channel:

Subscribers:

68,700

Published on December 17, 2020 6:18:45 AM ● Video Link: https://www.youtube.com/watch?v=Q4HEiV_kKUA

Duration: 44:20

2,099 views

Other Videos By Simons Institute for the Theory of Computing

2020-12-19	Recent Developments in Supervised Learning With Noise
2020-12-19	Testing and Reconstruction via Decision Trees
2020-12-18	An Equivalence Between Private Classification and Online Prediction
2020-12-18	Small Covers for Near-Zero Sets of Polynomials and Learning Latent Variable Models
2020-12-18	Hardness of Identity Testing for Potts models and RBMs
2020-12-18	Near-Optimal Learning of Tree-Structured Distributions by Chow-Liu
2020-12-17	Learning Some Ill-Conditioned Gaussian Graphical Models
2020-12-17	Directed Graphical Models for Extreme Value Statistics
2020-12-17	Learning Deep ReLU Networks is Fixed-Parameter Tractable
2020-12-17	The Surprising Simplicity of the Early-Time Learning Dynamics of Neural Networks in High Dimension
2020-12-16	Analyzing Optimization and Generalization in Deep Learning via Dynamics of Gradient Descent
2020-12-16	SGD Learns One-Layer Networks in WGANs
2020-12-16	Recent Progress in Algorithmic Robust Statistics via the Sum-of-Squares Method
2020-12-16	Phase Transitions for Detecting Latent Geometry in Random Graphs
2020-12-16	Low-Degree Hardness of Random Optimization Problems
2020-12-15	Counting and Sampling Subgraphs in Sublinear Time
2020-12-15	Learning and Testing for Gradient Descent
2020-12-15	Learning Ising Models from One, Ten or a Thousand Samples
2020-12-15	Reduction From Non-Unique Games to Boolean Unique Games
2020-12-15	Testing Noisy Linear Functions for Sparsity
2020-12-14	VC Dimension and Distribution-Free Sample-Based Testing

Tags:

Simons Institute

theoretical computer science

UC Berkeley

Computer Science

Theory of Computation

Theory of Computing

Learning and Testing in High Dimensions

Nadav Cohen