Skip to yearly menu bar Skip to main content


Talk
in
Workshop: Principled Approaches to Deep Learning

Invited Talk 6 - Nathan Srebro

[ ]
2017 Talk

Abstract:

Geometry, Optimization and Generalization in Multilayer Networks

What is it that enables learning with multi-layer networks? What causes the network to generalize well despite the model class having extremely high capacity? In this talk I will explore these questions through experimentation, analogy to matrix factorization (including some new results on the energy landscape and implicit regularization in matrix factorization), and study of alternate geometries and optimization approaches.

Chat is not available.