Home Page

Papers

Submissions

News

Editorial Board

Open Source Software

Proceedings (PMLR)

Transactions (TMLR)

Search

Statistics

Login

Frequently Asked Questions

Contact Us



RSS Feed

A Momentumized, Adaptive, Dual Averaged Gradient Method

Aaron Defazio, Samy Jelassi; 23(144):1−34, 2022.

Abstract

We introduce MADGRAD, a novel optimization method in the family of AdaGrad adaptive gradient methods. MADGRAD shows excellent performance on deep learning optimization problems from multiple fields, including classification and image-to-image tasks in vision, and recurrent and bidirectionally-masked models in natural language processing. For each of these tasks, MADGRAD matches or outperforms both SGD and ADAM in test set performance, even on problems for which adaptive methods normally perform poorly.

[abs][pdf][bib]        [code]
© JMLR 2022. (edit, beta)