Stochastic Optimization with Random Search
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918253618528256 |
|---|---|
| author | Chayti, El Mahdi Kadi, Taha El Bakkali El Saadi, Omar Jaggi, Martin |
| author_facet | Chayti, El Mahdi Kadi, Taha El Bakkali El Saadi, Omar Jaggi, Martin |
| contents | We revisit random search for stochastic optimization, where only noisy function evaluations are available. We show that the method works under weaker smoothness assumptions than previously considered, and that stronger assumptions enable improved guarantees. In the finite-sum setting, we design a variance-reduced variant that leverages multiple samples to accelerate convergence. Our analysis relies on a simple translation invariance property, which provides a principled way to balance noise and reduce variance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_15610 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Stochastic Optimization with Random Search Chayti, El Mahdi Kadi, Taha El Bakkali El Saadi, Omar Jaggi, Martin Optimization and Control Machine Learning We revisit random search for stochastic optimization, where only noisy function evaluations are available. We show that the method works under weaker smoothness assumptions than previously considered, and that stronger assumptions enable improved guarantees. In the finite-sum setting, we design a variance-reduced variant that leverages multiple samples to accelerate convergence. Our analysis relies on a simple translation invariance property, which provides a principled way to balance noise and reduce variance. |
| title | Stochastic Optimization with Random Search |
| topic | Optimization and Control Machine Learning |
| url | https://arxiv.org/abs/2510.15610 |