On the Optimal Regret of Locally Private Linear Contextual Bandit.

Jiachun Li David Simchi-Levi Yining Wang

Published in: CoRR (2024)

Keyphrases

upper confidence bound
contextual bandit
worst case
optimal linear
optimal solution
lower bound
online learning
regret bounds
data mining
privacy preserving
closed form
globally consistent
probabilistic model
dynamic programming
expert advice
information retrieval
machine learning