Oral: Federated Multi-armed Bandits with Personalization
Apr 14, 2021
Speakers
About
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 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.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 (P…
Organizer
AISTATS 2021
Account · 63 followers
Categories
AI & Data Science
Category · 10.8k presentations
About AISTATS 2021
The 24th International Conference on Artificial Intelligence and Statistics was held virtually from Tuesday, 13 April 2021 to Thursday, 15 April 2021.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Oral: A constrained risk inequality for general losses
Watch later
Feng Ruan, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Have We Learned to Explain? How Interpretability Methods Can Learn to Encode Predictions in their Interpretations.
Watch later
Neil Jethani, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
HIP-GP: Hierarchical Inducing Point Gaussian Process for Inter-domian Observations
Watch later
Luhuan Wu, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
A Bayesian nonparametric approach to count-min sketch under power-law data streams
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Causal Inference with Selectively Deconfounded Data
Watch later
Kyra Gan, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
On the Suboptimality of Negative Momentum for Minimax Optimization
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%