Communication-Efficient Distributed Learning with Differential Privacy
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914442066788352 |
|---|---|
| author | Ren, Xiaoxing Ma, Yuwen Bastianello, Nicola Johansson, Karl H. Parisini, Thomas Malikopoulos, Andreas A. |
| author_facet | Ren, Xiaoxing Ma, Yuwen Bastianello, Nicola Johansson, Karl H. Parisini, Thomas Malikopoulos, Andreas A. |
| contents | We address nonconvex learning problems over undirected networks. In particular, we focus on the challenge of designing an algorithm that is both communication-efficient and that guarantees the privacy of the agents' data. The first goal is achieved through a local training approach, which reduces communication frequency. The second goal is achieved by perturbing gradients during local training, specifically through gradient clipping and additive noise. We prove that the resulting algorithm converges to a stationary point of the problem within a bounded distance. Additionally, we provide theoretical privacy guarantees within a differential privacy framework that ensure agents' training data cannot be inferred from the trained model shared over the network. We show the algorithm's superior performance on a classification task under the same privacy budget, compared with state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_02558 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Communication-Efficient Distributed Learning with Differential Privacy Ren, Xiaoxing Ma, Yuwen Bastianello, Nicola Johansson, Karl H. Parisini, Thomas Malikopoulos, Andreas A. Machine Learning Optimization and Control We address nonconvex learning problems over undirected networks. In particular, we focus on the challenge of designing an algorithm that is both communication-efficient and that guarantees the privacy of the agents' data. The first goal is achieved through a local training approach, which reduces communication frequency. The second goal is achieved by perturbing gradients during local training, specifically through gradient clipping and additive noise. We prove that the resulting algorithm converges to a stationary point of the problem within a bounded distance. Additionally, we provide theoretical privacy guarantees within a differential privacy framework that ensure agents' training data cannot be inferred from the trained model shared over the network. We show the algorithm's superior performance on a classification task under the same privacy budget, compared with state-of-the-art methods. |
| title | Communication-Efficient Distributed Learning with Differential Privacy |
| topic | Machine Learning Optimization and Control |
| url | https://arxiv.org/abs/2604.02558 |