Collaborative Linear Bandits with Adversarial Agents: Near-Optimal Regret Bounds.

Aritra Mitra Arman Adibi George J. Pappas Hamed Hassani

Published in: NeurIPS (2022)

Keyphrases

regret bounds
multi agent
online learning
lower bound
linear regression
multi armed bandit
upper bound
bregman divergences
online convex optimization