Federated Frank-Wolfe Algorithm
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_ | 1866914916630265856 |
|---|---|
| author | Dadras, Ali Banerjee, Sourasekhar Prakhya, Karthik Yurtsever, Alp |
| author_facet | Dadras, Ali Banerjee, Sourasekhar Prakhya, Karthik Yurtsever, Alp |
| contents | Federated learning (FL) has gained a lot of attention in recent years for building privacy-preserving collaborative learning systems. However, FL algorithms for constrained machine learning problems are still limited, particularly when the projection step is costly. To this end, we propose a Federated Frank-Wolfe Algorithm (FedFW). FedFW features data privacy, low per-iteration cost, and communication of sparse signals. In the deterministic setting, FedFW achieves an $\varepsilon$-suboptimal solution within $O(\varepsilon^{-2})$ iterations for smooth and convex objectives, and $O(\varepsilon^{-3})$ iterations for smooth but non-convex objectives. Furthermore, we present a stochastic variant of FedFW and show that it finds a solution within $O(\varepsilon^{-3})$ iterations in the convex setting. We demonstrate the empirical performance of FedFW on several machine learning tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_10090 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Federated Frank-Wolfe Algorithm Dadras, Ali Banerjee, Sourasekhar Prakhya, Karthik Yurtsever, Alp Machine Learning Distributed, Parallel, and Cluster Computing Federated learning (FL) has gained a lot of attention in recent years for building privacy-preserving collaborative learning systems. However, FL algorithms for constrained machine learning problems are still limited, particularly when the projection step is costly. To this end, we propose a Federated Frank-Wolfe Algorithm (FedFW). FedFW features data privacy, low per-iteration cost, and communication of sparse signals. In the deterministic setting, FedFW achieves an $\varepsilon$-suboptimal solution within $O(\varepsilon^{-2})$ iterations for smooth and convex objectives, and $O(\varepsilon^{-3})$ iterations for smooth but non-convex objectives. Furthermore, we present a stochastic variant of FedFW and show that it finds a solution within $O(\varepsilon^{-3})$ iterations in the convex setting. We demonstrate the empirical performance of FedFW on several machine learning tasks. |
| title | Federated Frank-Wolfe Algorithm |
| topic | Machine Learning Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2408.10090 |