Skip to yearly menu bar Skip to main content


Plenary talk - Elad Hazan
in
Workshop: Beyond first order methods in machine learning systems

Adaptive gradient methods: efficient implementation and generalization

[ ]
2019 Plenary talk - Elad Hazan

Abstract:

Adaptive gradient methods have had a transformative impact in deep learning. We will describe recent theoretical and experimental advances in their understanding, including low-memory adaptive preconditioning, and insights into their generalizaton ability.

Live content is unavailable. Log in and register to view live content