The Stochastic Multi-Proximal Method for Nonsmooth Optimization
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918024034910208 |
|---|---|
| author | Condat, Laurent Gasanov, Elnur Richtárik, Peter |
| author_facet | Condat, Laurent Gasanov, Elnur Richtárik, Peter |
| contents | Stochastic gradient descent type methods are ubiquitous in machine learning, but they are only applicable to the optimization of differentiable functions. Proximal algorithms are more general and applicable to nonsmooth functions. We propose a new stochastic and variance-reduced algorithm, the Stochastic Multi-Proximal Method (SMPM), in which the proximity operators of a (possibly empty) random subset of functions are called at every iteration, according to an arbitrary sampling distribution. Several existing algorithms, including Point-SAGA (2016), Proxskip (2022) and RandProx-Minibatch (2023) are recovered as particular cases. We derive linear convergence results in presence of strong convexity and smoothness or similarity of the functions. We prove convergence in the general convex case and accelerated O(1/t2) convergence with varying stepsizes in presence of strong convexity solely. Our results are new even for the above special cases. Moreover, we show an application to distributed optimization with compressed communication, outperforming existing methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_12409 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | The Stochastic Multi-Proximal Method for Nonsmooth Optimization Condat, Laurent Gasanov, Elnur Richtárik, Peter Optimization and Control Stochastic gradient descent type methods are ubiquitous in machine learning, but they are only applicable to the optimization of differentiable functions. Proximal algorithms are more general and applicable to nonsmooth functions. We propose a new stochastic and variance-reduced algorithm, the Stochastic Multi-Proximal Method (SMPM), in which the proximity operators of a (possibly empty) random subset of functions are called at every iteration, according to an arbitrary sampling distribution. Several existing algorithms, including Point-SAGA (2016), Proxskip (2022) and RandProx-Minibatch (2023) are recovered as particular cases. We derive linear convergence results in presence of strong convexity and smoothness or similarity of the functions. We prove convergence in the general convex case and accelerated O(1/t2) convergence with varying stepsizes in presence of strong convexity solely. Our results are new even for the above special cases. Moreover, we show an application to distributed optimization with compressed communication, outperforming existing methods. |
| title | The Stochastic Multi-Proximal Method for Nonsmooth Optimization |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2505.12409 |