Byzantine-Robust Federated Linear Bandits [article]

Ali Jadbabaie, Haochuan Li, Jian Qian, Yi Tian
2022 arXiv   pre-print
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
more » ... lf of agents and achieves a sublinear 𝒪̃(T^3/4) regret with 𝒪(√(T)) steps of communication in T 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.
arXiv:2204.01155v1 fatcat:64deqod4xfcmnbj34jtybxvzpa