FSCLB scales federated linear contextual bandits with sketching to achieve over 90% lower computation and communication costs while preserving a near-optimal regret bound of O(sqrt(l d T)).
Federated multi-armed bandits.Proceedings of the AAAI Conference on Artificial Intelligence, 35(11):9603–9611, May 2021
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Scaling Federated Linear Contextual Bandits via Sketching
FSCLB scales federated linear contextual bandits with sketching to achieve over 90% lower computation and communication costs while preserving a near-optimal regret bound of O(sqrt(l d T)).