SARAH-based Variance-reduced Algorithm for Stochastic Finite-sum Cocoercive Variational Inequalities
This work addresses a specific class of variational inequalities relevant to machine learning, presenting an incremental improvement with practical applicability.
The paper tackles stochastic finite-sum cocoercive variational inequalities by investigating a SARAH-based variance-reduced algorithm, achieving linear convergence for strongly monotone problems, as confirmed by experiments.
Variational inequalities are a broad formalism that encompasses a vast number of applications. Motivated by applications in machine learning and beyond, stochastic methods are of great importance. In this paper we consider the problem of stochastic finite-sum cocoercive variational inequalities. For this class of problems, we investigate the convergence of the method based on the SARAH variance reduction technique. We show that for strongly monotone problems it is possible to achieve linear convergence to a solution using this method. Experiments confirm the importance and practical applicability of our approach.