Logo

Optimization and Generalization Property of Two-Layer Neural Network under Gradient Descent Dynamics

Speaker

Chengchao Zhao, Beijing Computational Science Research Center

Time

2019.10.23 12:20-13:50

Venue

Room 306, No.5 Science Building

Abstract

We introduce Weinan E, Chao Ma and Lei Wu’s work: optimization and generalization are two central issues in the theoretical analysis of machine learning models. They show that gradient descent dynamics can achieve zero training loss exponentially fast regardless of the quality of the labels and give some results on optimization and generalization.

Reference:

A Comparative Analysis of the Optimization and Generalization Property of Two-layer Neural Network and Random Feature Models Under Gradient Descent Dynamics