arXiv (Cornell University) · 2021 · 15 citations · 20 references
ComputingData ScienceDecision TheoryMachine LearningOptimizationExploration-exploitation TradeoffFederated LearningReinforcement LearningBalancing ExplorationBandit AlgorithmsBenchmark DatasetsExplorationLearningRegret Optimization
A general framework of personalized federated multi-armed bandits (PF-MAB) is proposed, which is a new bandit paradigm analogous to the federated learning (FL) framework in supervised learning and enjoys the features of FL with personalization. Under the PF-MAB framework, a mixed bandit learning problem that flexibly balances generalization and personalization is studied. A lower bound analysis for the mixed model is presented. We then propose the Personalized Federated Upper Confidence Bound (PF-UCB) algorithm, where the exploration length is chosen carefully to achieve the desired balance of learning the local model and supplying global information for the mixed learning objective. Theoretical analysis proves that PF-UCB achieves an $O(\log(T))$ regret regardless of the degree of personalization, and has a similar instance dependency as the lower bound. Experiments using both synthetic and real-world datasets corroborate the theoretical analysis and demonstrate the effectiveness of the proposed algorithm.
20
Communication-Efficient Learning of Deep Networks from Decentralized Data
H. Brendan McMahan, Eider Moore, Daniel Ramage et al. · arXiv (Cornell University) · 2016 · 5.2K citations · Full text
Advances and Open Problems in Federated Learning
Peter Kairouz, H. Brendan McMahan, Brendan Avent et al. · Foundations and Trends® in Machine Learning · 2020 · 4.7K citations · Full text
A contextual-bandit approach to personalized news article recommendation
Lihong Li, Wei Chu, John Langford et al. · 2010 · 2.5K citations · Full text
Asymptotically efficient adaptive allocation rules
Tze-Leung Lai, Herbert Robbins · Advances in Applied Mathematics · 1985 · 2.5K citations