Method with Batching for Stochastic Finite-Sum Variational Inequalities in Non-Euclidean Setting
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910603266752512 |
|---|---|
| author | Pichugin, Alexander Pechin, Maksim Beznosikov, Aleksandr Novitskii, Vasilii Gasnikov, Alexander |
| author_facet | Pichugin, Alexander Pechin, Maksim Beznosikov, Aleksandr Novitskii, Vasilii Gasnikov, Alexander |
| contents | Variational inequalities are a universal optimization paradigm that incorporate classical minimization and saddle point problems. Nowadays more and more tasks require to consider stochastic formulations of optimization problems. In this paper, we present an analysis of a method that gives optimal convergence estimates for monotone stochastic finite-sum variational inequalities. In contrast to the previous works, our method supports batching, does not lose the oracle complexity optimality and uses an arbitrary Bregman distance to take into account geometry of the problem. Paper provides experimental confirmation to algorithm's effectiveness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_06728 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Method with Batching for Stochastic Finite-Sum Variational Inequalities in Non-Euclidean Setting Pichugin, Alexander Pechin, Maksim Beznosikov, Aleksandr Novitskii, Vasilii Gasnikov, Alexander Optimization and Control Variational inequalities are a universal optimization paradigm that incorporate classical minimization and saddle point problems. Nowadays more and more tasks require to consider stochastic formulations of optimization problems. In this paper, we present an analysis of a method that gives optimal convergence estimates for monotone stochastic finite-sum variational inequalities. In contrast to the previous works, our method supports batching, does not lose the oracle complexity optimality and uses an arbitrary Bregman distance to take into account geometry of the problem. Paper provides experimental confirmation to algorithm's effectiveness. |
| title | Method with Batching for Stochastic Finite-Sum Variational Inequalities in Non-Euclidean Setting |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2408.06728 |