362 citations · 2.5k across the 76 of their papers we have counts for
10 papers · 1 filter
Surpassing Gradient Descent Provably: A Cyclic Incremental Method with Linear Convergence Rate
Aryan Mokhtari, Mert Gürbüzbalaban, Alejandro Ribeiro
Recently, there has been growing interest in developing optimization methods for solving large-scale machine learning problems. Most of these problems boil down to the problem of m…
Stochastic Averaging for Constrained Optimization with Application to Online Resource Allocation
Tianyi Chen, Aryan Mokhtari, Xin Wang +2
Existing approaches to resource allocation for nowadays stochastic networks are challenged to meet fast convergence and tolerable delay requirements. The present paper leverages on…
A Class of Parallel Doubly Stochastic Algorithms for Large-Scale Learning
Aryan Mokhtari, Alec Koppel, Alejandro Ribeiro
We consider learning problems over training sets in which both, the number of training examples and the dimension of the feature vectors, are large. To solve these problems we prop…
Adaptive Newton Method for Empirical Risk Minimization to Statistical Accuracy
Aryan Mokhtari, Alejandro Ribeiro
We consider empirical risk minimization for large-scale datasets. We introduce Ada Newton as an adaptive algorithm that uses Newton's method with adaptive sample sizes. The main id…
Decentralized Quasi-Newton Methods
Mark Eisen, Aryan Mokhtari, Alejandro Ribeiro
We introduce the decentralized Broyden-Fletcher-Goldfarb-Shanno (D-BFGS) method as a variation of the BFGS quasi-Newton method for solving decentralized optimization problems. The…
A Decentralized Second-Order Method for Dynamic Optimization
Aryan Mokhtari, Wei Shi, Qing Ling +1
This paper considers decentralized dynamic optimization problems where nodes of a network try to minimize a sequence of time-varying objective functions in a real-time scheme. At e…
A Decentralized Quasi-Newton Method for Dual Formulations of Consensus Optimization
Mark Eisen, Aryan Mokhtari, Alejandro Ribeiro
This paper considers consensus optimization problems where each node of a network has access to a different summand of an aggregate cost function. Nodes try to minimize the aggrega…
Doubly Random Parallel Stochastic Methods for Large Scale Learning
Aryan Mokhtari, Alec Koppel, Alejandro Ribeiro
We consider learning problems over training sets in which both, the number of training examples and the dimension of the feature vectors, are large. To solve these problems we prop…
Decentralized Prediction-Correction Methods for Networked Time-Varying Convex Optimization
Andrea Simonetto, Alec Koppel, Aryan Mokhtari +2
We develop algorithms that find and track the optimal solution trajectory of time-varying convex optimization problems which consist of local and network-related objectives. The al…
A Decentralized Second-Order Method with Exact Linear Convergence Rate for Consensus Optimization
Aryan Mokhtari, Wei Shi, Qing Ling +1
This paper considers decentralized consensus optimization problems where different summands of a global objective function are available at nodes of a network that can communicate…