Timezone: »

IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method
Yossi Arjevani · Joan Bruna · Bugra Can · Mert Gurbuzbalaban · Stefanie Jegelka · Hongzhou Lin

Wed Dec 09 09:00 AM -- 11:00 AM (PST) @ Poster Session 3 #1135

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 and SSDA. 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.

Author Information

Yossi Arjevani (NYU)
Joan Bruna (NYU)
Bugra Can (Rutgers University)
Mert Gurbuzbalaban (Rutgers)
Stefanie Jegelka (MIT)

Stefanie Jegelka is an X-Consortium Career Development Assistant Professor in the Department of EECS at MIT. She is a member of the Computer Science and AI Lab (CSAIL), the Center for Statistics and an affiliate of the Institute for Data, Systems and Society and the Operations Research Center. Before joining MIT, she was a postdoctoral researcher at UC Berkeley, and obtained her PhD from ETH Zurich and the Max Planck Institute for Intelligent Systems. Stefanie has received a Sloan Research Fellowship, an NSF CAREER Award, a DARPA Young Faculty Award, the German Pattern Recognition Award and a Best Paper Award at the International Conference for Machine Learning (ICML). Her research interests span the theory and practice of algorithmic machine learning.

Hongzhou Lin (MIT)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors