362 citations · 2.5k across the 76 of their papers we have counts for
5 papers · 2 filters
Achieving Acceleration in Distributed Optimization via Direct Discretization of the Heavy-Ball ODE
Jingzhao Zhang, César A. Uribe, Aryan Mokhtari +1
We develop a distributed algorithm for convex Empirical Risk Minimization, the problem of minimizing large but finite sum of convex functions over networks. The proposed algorithm…
A Primal-Dual Quasi-Newton Method for Exact Consensus Optimization
Mark Eisen, Aryan Mokhtari, Alejandro Ribeiro
We introduce the primal-dual quasi-Newton (PD-QN) method as an approximated second order method for solving decentralized optimization problems. The PD-QN method performs quasi-New…
Direct Runge-Kutta Discretization Achieves Acceleration
Jingzhao Zhang, Aryan Mokhtari, Suvrit Sra +1
We study gradient-based optimization methods obtained by directly discretizing a second-order ordinary differential equation (ODE) related to the continuous limit of Nesterov's acc…
Stochastic Conditional Gradient Methods: From Convex Minimization to Submodular Maximization
Aryan Mokhtari, Hamed Hassani, Amin Karbasi
This paper considers stochastic optimization problems for a large class of objective functions, including convex and continuous submodular. Stochastic proximal gradient methods hav…
Decentralized Submodular Maximization: Bridging Discrete and Continuous Settings
Aryan Mokhtari, Hamed Hassani, Amin Karbasi
In this paper, we showcase the interplay between discrete and continuous optimization in network-structured settings. We propose the first fully decentralized optimization method f…