Online Multi-Agent Decentralized Byzantine-robust Gradient Estimation
Not on the map. Why?
Abstract (arXiv)
In this paper, we propose an iterative scheme for distributed Byzantineresilient estimation of a gradient associated with a black-box model. Our algorithm is based on simultaneous perturbation, secure state estimation and two-timescale stochastic approximations. We also show the performance of our algorithm through numerical experiments.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 7 of its 13 references that are in the map. First posted on arXiv 30 Sep 2022.
Builds on
7 of 13 references.
References · 7
- 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
- 2014Convex Optimization: Algorithms and Complexitycited by 575
- 2019Federated Variance-Reduced Stochastic Gradient Descent with Robustness to Byzantine Attackscited by 79
- 2017Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descentcited by 59
- 2015Gradient Estimation with Simultaneous Perturbation and Compressive Sensingcited by 2
- 2013Storage and Search in Dynamic Peer-to-Peer Networkscited by 1
- 2013Asynchronous Gossip for Averaging and Spectral Rankingcited by 1
Built on by
Not cited yet.