A Stochastic Halpern Iteration with Variance Reduction for Stochastic Monotone Inclusion Problems

by   Xufeng Cai, et al.

We study stochastic monotone inclusion problems, which widely appear in machine learning applications, including robust regression and adversarial learning. We propose novel variants of stochastic Halpern iteration with recursive variance reduction. In the cocoercive – and more generally Lipschitz-monotone – setup, our algorithm attains ϵ norm of the operator with 𝒪(1/ϵ^3) stochastic operator evaluations, which significantly improves over state of the art 𝒪(1/ϵ^4) stochastic operator evaluations required for existing monotone inclusion solvers applied to the same problem classes. We further show how to couple one of the proposed variants of stochastic Halpern iteration with a scheduled restart scheme to solve stochastic monotone inclusion problems with 𝒪(log(1/ϵ)/ϵ^2) stochastic operator evaluations under additional sharpness or strong monotonicity assumptions. Finally, we argue via reductions between different problem classes that our stochastic oracle complexity bounds are tight up to logarithmic factors in terms of their ϵ-dependence.


page 1

page 2

page 3

page 4


Simple and optimal methods for stochastic variational inequalities, I: operator extrapolation

In this paper we first present a novel operator extrapolation (OE) metho...

Distributed Forward-Backward Methods without Central Coordination

In this work, we propose and analyse forward-backward-type algorithms fo...

A Single-Timescale Analysis For Stochastic Approximation With Multiple Coupled Sequences

Stochastic approximation (SA) with multiple coupled sequences has found ...

A Unifying Framework for Variance Reduction Algorithms for Finding Zeroes of Monotone Operators

A wide range of optimization problems can be recast as monotone inclusio...

Geometry-Aware Universal Mirror-Prox

Mirror-prox (MP) is a well-known algorithm to solve variational inequali...

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

We consider monotone inclusion problems where the operators may be expec...

Please sign up or login with your details

Forgot password? Click here to reset