Byzantine-Robust Federated Linear Bandits
Ali Jadbabaie, Haochuan Li, Jian Qian, Yi Tian

TL;DR
This paper introduces a robust federated linear bandit algorithm resilient to Byzantine attacks, achieving sublinear regret, differential privacy, and improved bounds with known corruption levels.
Contribution
We propose a novel Byzantine-robust federated linear bandit algorithm using geometric median aggregation, with proven robustness, privacy guarantees, and improved regret bounds under certain conditions.
Findings
Robust to Byzantine attacks on fewer than half of agents
Achieves sublinear regret of rac{T^{3/4}}{}
Ensures differential privacy via a tree-based mechanism
Abstract
In this paper, we study a linear bandit optimization problem in a federated setting where a large collection of distributed agents collaboratively learn a common linear bandit model. Standard federated learning algorithms applied to this setting are vulnerable to Byzantine attacks on even a small fraction of agents. We propose a novel algorithm with a robust aggregation oracle that utilizes the geometric median. We prove that our proposed algorithm is robust to Byzantine attacks on fewer than half of agents and achieves a sublinear regret with steps of communication in steps. Moreover, we make our algorithm differentially private via a tree-based mechanism. Finally, if the level of corruption is known to be small, we show that using the geometric median of mean oracle for robust aggregation further improves the regret bound.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsPrivacy-Preserving Technologies in Data · Advanced Bandit Algorithms Research · Stochastic Gradient Optimization Techniques
