# Robust Online and Distributed Mean Estimation Under Adversarial Data Corruption

arXiv: https://arxiv.org/abs/2209.09624 · HTML: https://mlsanity.com/paper/2209.09624/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 17 references that are in the map.
- First posted on arXiv 17 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)
- [Mean estimation and regression under heavy-tailed distributions--a survey](https://mlsanity.com/paper/1906.04280/) (2019)
- [Outlier Robust Mean Estimation with Subgaussian Rates via Stability](https://mlsanity.com/paper/2007.15618/) (2020)
- [Distributed Cooperative Decision-Making in Multiarmed Bandits: Frequentist and Bayesian Algorithms](https://mlsanity.com/paper/1606.00911/) (2016)
- [Cooperative Multi-Agent Bandits with Heavy Tails](https://mlsanity.com/paper/2008.06244/) (2020)
- [A New Approach to Distributed Hypothesis Testing and Non-Bayesian Learning: Improved Learning Rate and Byzantine-Resilience](https://mlsanity.com/paper/1907.03588/) (2019)
- [Distributed Estimation of Sparse Inverse Covariances](https://mlsanity.com/paper/2109.12020/) (2021)

## Built on by (most cited first, 5 of 5)

- [Byzantine-Robust Distributed Online Learning: Taming Adversarial Participants in An Adversarial Environment](https://mlsanity.com/paper/2307.07980/) (2023)
- [Online Robust Mean Estimation](https://mlsanity.com/paper/2310.15932/) (2023)
- [Corruption-Tolerant Asynchronous Q-Learning with Near-Optimal Rates](https://mlsanity.com/paper/2509.08933/) (2025)
- [Robust Online Covariance and Sparse Precision Estimation Under Arbitrary Data Corruption](https://mlsanity.com/paper/2309.08884/) (2023)
- [Robust Asynchronous Q-Learning under Reward and State Corruption via Batching](https://mlsanity.com/paper/2607.20822/) (2026)

## Abstract (arXiv)

We study robust mean estimation in an online and distributed scenario in the presence of adversarial data attacks. At each time step, each agent in a network receives a potentially corrupted data point, where the data points were originally independent and identically distributed samples of a random variable. We propose online and distributed algorithms for all agents to asymptotically estimate the mean. We provide the error-bound and the convergence properties of the estimates to the true mean under our algorithms. Based on the network topology, we further evaluate each agent's trade-off in convergence rate between incorporating data from neighbors and learning with only local observations.