Almost Cost-Free Communication in Federated Best Arm Identification
Kota Srinivas Reddy, P. N. Karthik, and Vincent Y. F. Tan

TL;DR
This paper introduces FedElim, a federated bandit algorithm that minimizes communication costs while accurately identifying best arms, demonstrating that near-cost-free communication is achievable with high probability.
Contribution
The paper proposes FedElim, a novel algorithm for federated best arm identification that reduces communication to near-zero costs while maintaining high accuracy, and provides theoretical and empirical validation.
Findings
FedElim achieves near-cost-free communication with minimal total cost.
The total number of arm selections is at most twice that of a fully communicating variant.
Communication cost is shown to be almost negligible compared to arm selection costs.
Abstract
We study the problem of best arm identification in a federated learning multi-armed bandit setup with a central server and multiple clients. Each client is associated with a multi-armed bandit in which each arm yields {\em i.i.d.}\ rewards following a Gaussian distribution with an unknown mean and known variance. The set of arms is assumed to be the same at all the clients. We define two notions of best arm -- local and global. The local best arm at a client is the arm with the largest mean among the arms local to the client, whereas the global best arm is the arm with the largest average mean across all the clients. We assume that each client can only observe the rewards from its local arms and thereby estimate its local best arm. The clients communicate with a central server on uplinks that entail a cost of units per usage per uplink. The global best arm is estimated at the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
TopicsAdvanced Bandit Algorithms Research · Age of Information Optimization · Distributed Sensor Networks and Detection Algorithms
