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

Aritra Mitra Arman Adibi George J. Pappas Hamed Hassani

Published in: CoRR (2022)

Keyphrases

regret bounds
multi agent
lower bound
linear regression
online learning
multi armed bandit
upper bound
principal component analysis
feature selection
pairwise