Stochastic variance reduction for variational inequality methods

A Alacaoglu, Y Malitsky - Conference on Learning Theory, 2022 - proceedings.mlr.press
We propose stochastic variance reduced algorithms for solving convex-concave saddle
point problems, monotone variational inequalities, and monotone inclusions. Our framework …

[HTML][HTML] Convergence of sequences: A survey

B Franci, S Grammatico - Annual Reviews in Control, 2022 - Elsevier
Convergent sequences of real numbers play a fundamental role in many different problems
in system theory, eg, in Lyapunov stability analysis, as well as in optimization theory and …

Solving stochastic weak minty variational inequalities without increasing batch size

T Pethick, O Fercoq, P Latafat, P Patrinos… - arXiv preprint arXiv …, 2023 - arxiv.org
This paper introduces a family of stochastic extragradient-type algorithms for a class of
nonconvex-nonconcave problems characterized by the weak Minty variational inequality …

A stochastic primal-dual algorithm for composite constrained optimization

E Su, Z Hu, W Xie, L Li, W Zhang - Neurocomputing, 2024 - Elsevier
This paper studies the decentralized stochastic optimization problem over an undirected
network, where each agent owns its local private functions made up of two non-smooth …

No-regret learning in games with noisy feedback: Faster rates and adaptivity via learning rate separation

YG Hsieh, K Antonakopoulos… - Advances in …, 2022 - proceedings.neurips.cc
We examine the problem of regret minimization when the learner is involved in a continuous
game with other optimizing agents: in this case, if all players follow a no-regret algorithm, it is …

Two Steps at a Time---Taking GAN Training in Stride with Tseng's Method

A Bohm, M Sedlmayer, ER Csetnek, RI Bot - SIAM Journal on Mathematics of …, 2022 - SIAM
Motivated by the training of generative adversarial networks (GANs), we study methods for
solving minimax problems with additional nonsmooth regularizers. We do so by employing …

Stochastic generalized Nash equilibrium-seeking in merely monotone games

B Franci, S Grammatico - IEEE Transactions on Automatic …, 2021 - ieeexplore.ieee.org
We solve the stochastic generalized Nash equilibrium (SGNE) problem in merely monotone
games with expected value cost functions. Specifically, we present the first distributed SGNE …

Variable sample-size optimistic mirror descent algorithm for stochastic mixed variational inequalities

ZP Yang, Y Zhao, GH Lin - Journal of Global Optimization, 2024 - Springer
In this paper, we propose a variable sample-size optimistic mirror descent algorithm under
the Bregman distance for a class of stochastic mixed variational inequalities. Different from …

Stochastic variance-reduced forward-reflected methods for root-finding problems

Q Tran-Dinh - arXiv preprint arXiv:2406.00937, 2024 - arxiv.org
We develop two novel stochastic variance-reduction methods to approximate a solution of
root-finding problems applicable to both equations and inclusions. Our algorithms leverage …

A fast stochastic approximation-based subgradient extragradient algorithm with variance reduction for solving stochastic variational inequality problems

XJ Long, YH He - Journal of Computational and Applied Mathematics, 2023 - Elsevier
In this paper, we propose a fast stochastic approximation-based subgradient extragradient
algorithm with variance reduction for solving the stochastic variational inequality, where the …