Personalized Federated X -armed Bandit
This addresses the problem of optimizing personalized objectives in federated learning for clients with heterogeneous data, though it appears incremental as it builds on existing federated and bandit methods.
The paper tackles the personalized federated X-armed bandit problem by proposing the PF-PNE algorithm with a double elimination strategy, which optimizes heterogeneous local objectives while protecting client data confidentiality, and it outperforms baselines on synthetic and real datasets.
In this work, we study the personalized federated $\mathcal{X}$-armed bandit problem, where the heterogeneous local objectives of the clients are optimized simultaneously in the federated learning paradigm. We propose the \texttt{PF-PNE} algorithm with a unique double elimination strategy, which safely eliminates the non-optimal regions while encouraging federated collaboration through biased but effective evaluations of the local objectives. The proposed \texttt{PF-PNE} algorithm is able to optimize local objectives with arbitrary levels of heterogeneity, and its limited communications protects the confidentiality of the client-wise reward data. Our theoretical analysis shows the benefit of the proposed algorithm over single-client algorithms. Experimentally, \texttt{PF-PNE} outperforms multiple baselines on both synthetic and real life datasets.