A Stochastic Proximal Point Algorithm for Saddle-Point Problems

09/13/2019
by   Luo Luo, et al.
0

We consider saddle point problems which objective functions are the average of n strongly convex-concave individual components. Recently, researchers exploit variance reduction methods to solve such problems and achieve linear-convergence guarantees. However, these methods have a slow convergence when the condition number of the problem is very large. In this paper, we propose a stochastic proximal point algorithm, which accelerates the variance reduction method SAGA for saddle point problems. Compared with the catalyst framework, our algorithm reduces a logarithmic term of condition number for the iteration complexity. We adopt our algorithm to policy evaluation and the empirical results show that our method is much more efficient than state-of-the-art methods.

READ FULL TEXT

page 1

page 2

page 3

page 4

04/01/2022

A Semismooth Newton Stochastic Proximal Point Algorithm with Variance Reduction

We develop an implementable stochastic proximal point (SPP) method for a...
03/19/2014

A Proximal Stochastic Gradient Method with Progressive Variance Reduction

We consider the problem of minimizing the sum of two convex functions: o...
06/17/2022

RECAPP: Crafting a More Efficient Catalyst for Convex Optimization

The accelerated proximal point algorithm (APPA), also known as "Catalyst...
08/26/2020

Variance-Reduced Proximal and Splitting Schemes for Monotone Stochastic Generalized Equations

We consider monotone inclusion problems where the operators may be expec...
07/31/2019

Robust stochastic optimization with the proximal point method

Standard results in stochastic convex optimization bound the number of s...
06/24/2015

Un-regularizing: approximate proximal point and faster stochastic algorithms for empirical risk minimization

We develop a family of accelerated stochastic algorithms that minimize s...
03/05/2016

A single-phase, proximal path-following framework

We propose a new proximal, path-following framework for a class of const...