Variance Reduction and Low Sample Complexity in Stochastic Optimization via Proximal Point Method
Guardado en:
| Publicado en: | arXiv.org (Feb 14, 2024), p. n/a |
|---|---|
| Autor principal: | |
| Publicado: |
Cornell University Library, arXiv.org
|
| Materias: | |
| Acceso en línea: | Citation/Abstract Full text outside of ProQuest |
| Etiquetas: |
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| Resumen: | This paper proposes a stochastic proximal point method to solve a stochastic convex composite optimization problem. High probability results in stochastic optimization typically hinge on restrictive assumptions on the stochastic gradient noise, for example, sub-Gaussian distributions. Assuming only weak conditions such as bounded variance of the stochastic gradient, this paper establishes a low sample complexity to obtain a high probability guarantee on the convergence of the proposed method. Additionally, a notable aspect of this work is the development of a subroutine to solve the proximal subproblem, which also serves as a novel technique for variance reduction. |
|---|---|
| ISSN: | 2331-8422 |
| Fuente: | Engineering Database |