Improved Algorithms for Bandit with Graph Feedback via Regret Decomposition.

Yuchen He Chihao Zhang

Published in: CoRR (2022)

Keyphrases

bandit problems
graph theory
multi armed bandit
upper confidence bound
learning algorithm
regret bounds
online learning
directed graph
regret minimization
data structure
lower bound
relevance feedback
worst case
optimization problems
random sampling
online algorithms