One-Point Feedback for Composite Optimization with Applications to Distributed and Federated Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2021
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918101915795456 |
|---|---|
| author | Beznosikov, Aleksandr Stepanov, Ivan Voronov, Artyom Gasnikov, Alexander |
| author_facet | Beznosikov, Aleksandr Stepanov, Ivan Voronov, Artyom Gasnikov, Alexander |
| contents | This work is devoted to solving the composite optimization problem with the mixture oracle: for the smooth part of the problem, we have access to the gradient, and for the non-smooth part, only the one-point zero-order oracle is available. For such a setup, we present a new method based on the sliding algorithm. Our method allows to separate the oracle complexities and to compute the gradient for one of the functions as rarely as possible. The paper also presents the applicability of our new method to the problems of distributed optimization and federated learning. Experimental results confirm the theory. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2107_05951 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | One-Point Feedback for Composite Optimization with Applications to Distributed and Federated Learning Beznosikov, Aleksandr Stepanov, Ivan Voronov, Artyom Gasnikov, Alexander Optimization and Control Distributed, Parallel, and Cluster Computing This work is devoted to solving the composite optimization problem with the mixture oracle: for the smooth part of the problem, we have access to the gradient, and for the non-smooth part, only the one-point zero-order oracle is available. For such a setup, we present a new method based on the sliding algorithm. Our method allows to separate the oracle complexities and to compute the gradient for one of the functions as rarely as possible. The paper also presents the applicability of our new method to the problems of distributed optimization and federated learning. Experimental results confirm the theory. |
| title | One-Point Feedback for Composite Optimization with Applications to Distributed and Federated Learning |
| topic | Optimization and Control Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2107.05951 |