Byzantine-Robust Gossip: Insights from a Dual Approach
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_ | 1866916822827139072 |
|---|---|
| author | Gaucher, Renaud Dieuleveut, Aymeric Hendrikx, Hadrien |
| author_facet | Gaucher, Renaud Dieuleveut, Aymeric Hendrikx, Hadrien |
| contents | Distributed learning has many computational benefits but is vulnerable to attacks from a subset of devices transmitting incorrect information. This paper investigates Byzantine-resilient algorithms in a decentralized setting, where devices communicate directly in a peer-to-peer manner within a communication network. We leverage the so-called dual approach for decentralized optimization and propose a Byzantine-robust algorithm. We provide convergence guarantees in the average consensus subcase, discuss the potential of the dual approach beyond this subcase, and re-interpret existing algorithms using the dual framework. Lastly, we experimentally show the soundness of our method. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_03449 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Byzantine-Robust Gossip: Insights from a Dual Approach Gaucher, Renaud Dieuleveut, Aymeric Hendrikx, Hadrien Machine Learning Distributed learning has many computational benefits but is vulnerable to attacks from a subset of devices transmitting incorrect information. This paper investigates Byzantine-resilient algorithms in a decentralized setting, where devices communicate directly in a peer-to-peer manner within a communication network. We leverage the so-called dual approach for decentralized optimization and propose a Byzantine-robust algorithm. We provide convergence guarantees in the average consensus subcase, discuss the potential of the dual approach beyond this subcase, and re-interpret existing algorithms using the dual framework. Lastly, we experimentally show the soundness of our method. |
| title | Byzantine-Robust Gossip: Insights from a Dual Approach |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2405.03449 |