# Private and Byzantine-Proof Cooperative Decision-Making

arXiv: https://arxiv.org/abs/2205.14174 · HTML: https://mlsanity.com/paper/2205.14174/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 45 references that are in the map.
- First posted on arXiv 27 May 2022.

## Builds on (most cited first, 14 of 14)

- [Online Clustering of Bandits](https://mlsanity.com/paper/1401.8257/) (2014)
- [Differentially Private Contextual Linear Bandits](https://mlsanity.com/paper/1810.00068/) (2018)
- [Delay and Cooperation in Nonstochastic Bandits](https://mlsanity.com/paper/1602.04741/) (2016)
- [Distributed Clustering of Linear Bandits in Peer to Peer Networks](https://mlsanity.com/paper/1604.07706/) (2016)
- [A Gang of Bandits](https://mlsanity.com/paper/1306.0811/) (2013)
- [Distributed Cooperative Decision-Making in Multiarmed Bandits: Frequentist and Bayesian Algorithms](https://mlsanity.com/paper/1606.00911/) (2016)
- [Algorithms for Differentially Private Multi-Armed Bandits](https://mlsanity.com/paper/1511.08681/) (2015)
- [On Context-Dependent Clustering of Bandits](https://mlsanity.com/paper/1608.03544/) (2016)
- [On Distributed Cooperative Decision-Making in Multiarmed Bandits](https://mlsanity.com/paper/1512.06888/) (2015)
- [Achieving Privacy in the Adversarial Multi-Armed Bandit](https://mlsanity.com/paper/1701.04222/) (2017)
- [Best Arm Identification for Contaminated Bandits](https://mlsanity.com/paper/1802.09514/) (2018)
- [Individual Regret in Cooperative Nonstochastic Multi-Armed Bandits](https://mlsanity.com/paper/1907.03346/) (2019)
- [A Unified Approach to Robust Mean Estimation](https://mlsanity.com/paper/1907.00927/) (2019)
- [Thompson Sampling on Symmetric α-Stable Bandits](https://mlsanity.com/paper/1907.03821/) (2019)

## Built on by (most cited first, 10 of 10)

- [Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance](https://mlsanity.com/paper/2402.01096/) (2024)
- [Byzantine-Robust Online and Offline Distributed Reinforcement Learning](https://mlsanity.com/paper/2206.00165/) (2022)
- [Federated Linear Contextual Bandits with User-level Differential Privacy](https://mlsanity.com/paper/2306.05275/) (2023)
- [Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Bounds](https://mlsanity.com/paper/2206.02834/) (2022)
- [Dynamic Global Sensitivity for Differentially Private Contextual Bandits](https://mlsanity.com/paper/2208.14555/) (2022)
- [Byzantine-Resilient Decentralized Multi-Armed Bandits](https://mlsanity.com/paper/2310.07320/) (2023)
- [Decentralized Blockchain-based Robust Multi-agent Multi-armed Bandit](https://mlsanity.com/paper/2402.04417/) (2024)
- [Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups](https://mlsanity.com/paper/2409.19092/) (2024)
- [Adversarial Attacks on Cooperative Multi-agent Bandits](https://mlsanity.com/paper/2311.01698/) (2023)
- [Learning from Unreliable Trajectories: Adversarially-Robust Federated Q-Learning](https://mlsanity.com/paper/2610.06918/) (2026)

## Abstract (arXiv)

The cooperative bandit problem is a multi-agent decision problem involving a group of agents that interact simultaneously with a multi-armed bandit, while communicating over a network with delays. The central idea in this problem is to design algorithms that can efficiently leverage communication to obtain improvements over acting in isolation. In this paper, we investigate the stochastic bandit problem under two settings - (a) when the agents wish to make their communication private with respect to the action sequence, and (b) when the agents can be byzantine, i.e., they provide (stochastically) incorrect information. For both these problem settings, we provide upper-confidence bound algorithms that obtain optimal regret while being (a) differentially-private and (b) tolerant to byzantine agents. Our decentralized algorithms require no information about the network of connectivity between agents, making them scalable to large dynamic systems. We test our algorithms on a competitive benchmark of random graphs and demonstrate their superior performance with respect to existing robust algorithms. We hope that our work serves as an important step towards creating distributed decision-making systems that maintain privacy.