# Online Multi-Agent Decentralized Byzantine-robust Gradient Estimation

arXiv: https://arxiv.org/abs/2209.15274 · HTML: https://mlsanity.com/paper/2209.15274/

## 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 (most cited first, 7 of 7)

- [Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates](https://mlsanity.com/paper/1803.01498/) (2018)
- [Convex Optimization: Algorithms and Complexity](https://mlsanity.com/paper/1405.4980/) (2014)
- [Federated Variance-Reduced Stochastic Gradient Descent with Robustness to Byzantine Attacks](https://mlsanity.com/paper/1912.12716/) (2019)
- [Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descent](https://mlsanity.com/paper/1705.05491/) (2017)
- [Gradient Estimation with Simultaneous Perturbation and Compressive Sensing](https://mlsanity.com/paper/1511.08768/) (2015)
- [Storage and Search in Dynamic Peer-to-Peer Networks](https://mlsanity.com/paper/1305.1121/) (2013)
- [Asynchronous Gossip for Averaging and Spectral Ranking](https://mlsanity.com/paper/1309.7841/) (2013)

## 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.