Tutorial

Random Matrix Theory and ML (RMT+ML)

Fabian Pedregosa · Courtney Paquette · Thomas Trogdon · Jeffrey Pennington

Abstract:

In recent years, random matrix theory (RMT) has come to the forefront of learning theory as a tool to understand some of its most important challenges. From generalization of deep learning models to a precise analysis of optimization algorithms, RMT provides analytically tractable models.

Chat is not available.

Schedule
Mon 12:00 p.m. - 12:05 p.m.
Live Intro (Introduction by moderator)   
Mon 12:05 p.m. - 1:06 p.m.
Introduction (Tutorial)   
Fabian Pedregosa, Courtney Paquette
Mon 1:06 p.m. - 1:30 p.m.
Q&A (Live Q&A)
Mon 1:30 p.m. - 2:00 p.m.
Analysis of numerical algorithms (Tutorial)   
Thomas Trogdon
Mon 2:00 p.m. - 2:15 p.m.
Q&A (Live Q&A)
Mon 2:15 p.m. - 2:45 p.m.
The Mystery of Generalization: Why Does Deep Learning Work? (Tutorial)   
Jeffrey Pennington
Mon 2:45 p.m. - 3:00 p.m.
Q&A (Live Q&A)