Online (Multinomial) Logistic Bandit: Improved Regret and Constant Computation Cost.

Yu-Jie Zhang Masashi Sugiyama

Published in: NeurIPS (2023)

Keyphrases

online learning
regret bounds
bandit problems
online convex optimization
online algorithms
lower bound
upper confidence bound
logistic regression
multi armed bandit
real time
high cost
training data
decision problems
naive bayes
search costs
probabilistic model
multi armed bandit problems