Bugra Can — accepted AI-conference papers

2020

IDEAL: Inexact DEcentralized Accelerated Augmented Lagrangian Method

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

NeurIPS 2020spotlight

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…

Cited by 28 Source ↗PDF ↗Scholar ↗

2019

Accelerated Linear Convergence of Stochastic Momentum Methods in Wasserstein Distances

Bugra Can, Mert Gurbuzbalaban, Lingjiong Zhu

ICML 2019oral

Momentum methods such as Polyak’s heavy ball (HB) method, Nesterov’s accelerated gradient (AG) as well as accelerated projected gradient (APG) method have been commonly used in machine learning practice, but their performance is quite sensitive to noise in the gradients. We study these methods under…

Cited by 54 Source ↗PDF ↗Scholar ↗