IDEAL: Inexact decentralized accelerated augmented Lagrangian method

Yossi Arjevani, Joan Bruna, Bugra Can, Mert Gürbüzbalaban, Stefanie Jegelka, Hongzhou Lin

Research output: Contribution to journalConference articlepeer-review

7 Scopus citations

Abstract

We introduce a framework for designing primal methods under the decentralized optimization setting where local functions are smooth and strongly convex. Our approach consists of approximately solving a sequence of sub-problems induced by the accelerated augmented Lagrangian method, thereby providing a systematic way for deriving several well-known decentralized algorithms including EXTRA [47] and SSDA [43]. When coupled with accelerated gradient descent, our framework yields a novel primal algorithm whose convergence rate is optimal and matched by recently derived lower bounds. We provide experimental results that demonstrate the effectiveness of the proposed algorithm on highly ill-conditioned problems.

Original languageAmerican English
JournalAdvances in Neural Information Processing Systems
Volume2020-December
StatePublished - 2020
Externally publishedYes
Event34th Conference on Neural Information Processing Systems, NeurIPS 2020 - Virtual, Online
Duration: 6 Dec 202012 Dec 2020

Bibliographical note

Publisher Copyright:
© 2020 Neural information processing systems foundation. All rights reserved.

Cite this