Variance Reduction for Matrix Games
Optimization and Control
2019-12-03 v2 Data Structures and Algorithms
Machine Learning
Abstract
We present a randomized primal-dual algorithm that solves the problem to additive error in time , for matrix with larger dimension and nonzero entries. This improves the best known exact gradient methods by a factor of and is faster than fully stochastic gradient methods in the accurate and/or sparse regime . Our results hold for in the simplex (matrix games, linear programming) and for in an ball and in the simplex (perceptron / SVM, minimum enclosing ball). Our algorithm combines Nemirovski's "conceptual prox-method" and a novel reduced-variance gradient estimator based on "sampling from the difference" between the current iterate and a reference point.
Cite
@article{arxiv.1907.02056,
title = {Variance Reduction for Matrix Games},
author = {Yair Carmon and Yujia Jin and Aaron Sidford and Kevin Tian},
journal= {arXiv preprint arXiv:1907.02056},
year = {2019}
}