Delay-tolerant distributed Bregman proximal algorithms.
Saved in:
| Title: | Delay-tolerant distributed Bregman proximal algorithms. |
|---|---|
| Authors: | Chraibi, S.1 (AUTHOR) selim.chraibi@univ-grenoble-alpes.fr, Iutzeler, F.2 (AUTHOR), Malick, J.2 (AUTHOR), Rogozin, A.3 (AUTHOR) |
| Source: | Optimization Methods & Software. Oct2025, Vol. 40 Issue 5, p1072-1088. 17p. |
| Subjects: | Distributed algorithms, Distributed computing, Subgradient methods, Cost functions, Delay-tolerant networks, Machine learning, Inverse problems |
| Abstract: | Many problems in machine learning write as the minimization of a sum of individual loss functions over the training examples. These functions are usually differentiable but, in some cases, their gradients are not Lipschitz continuous, which compromises the use of (proximal) gradient algorithms. Fortunately, changing the geometry and using Bregman divergences can alleviate this issue in several applications, such as for Poisson linear inverse problems. However, the Bregman operation makes the aggregation of several points and gradients more involved, hindering the distribution of computations for such problems. In this paper, we propose an asynchronous variant of the Bregman proximal-gradient method, able to adapt to any centralized computing system. In particular, we prove that the algorithm copes with arbitrarily long delays and we illustrate its behaviour on distributed Poisson inverse problems. [ABSTRACT FROM AUTHOR] |
| Copyright of Optimization Methods & Software is the property of Taylor & Francis Ltd and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| Abstract: | Many problems in machine learning write as the minimization of a sum of individual loss functions over the training examples. These functions are usually differentiable but, in some cases, their gradients are not Lipschitz continuous, which compromises the use of (proximal) gradient algorithms. Fortunately, changing the geometry and using Bregman divergences can alleviate this issue in several applications, such as for Poisson linear inverse problems. However, the Bregman operation makes the aggregation of several points and gradients more involved, hindering the distribution of computations for such problems. In this paper, we propose an asynchronous variant of the Bregman proximal-gradient method, able to adapt to any centralized computing system. In particular, we prove that the algorithm copes with arbitrarily long delays and we illustrate its behaviour on distributed Poisson inverse problems. [ABSTRACT FROM AUTHOR] |
|---|---|
| ISSN: | 10556788 |
| DOI: | 10.1080/10556788.2023.2278089 |
