Thompson Sampling for Stochastic Bandits with Noisy Contexts: An Information-Theoretic Regret Analysis.

Sharu Theresa Jose Shana Moothedath

Published in: CoRR (2024)

Keyphrases

information theoretic
mutual information
information theory
lower bound
multi class
theoretic framework
entropy measure
multi armed bandit
regret bounds
information bottleneck
pattern recognition
online learning
statistical analysis
bregman divergences
relative entropy
multi armed bandits