Syndicated Bandits: A Framework for Auto Tuning Hyper-parameters in Contextual Bandit Algorithms.

Qin Ding Yi-Wei Liu Cho-Jui Hsieh James Sharpnack

Published in: CoRR (2021)

Keyphrases

contextual bandit
upper confidence bound
support vector
hyperparameters
learning algorithm
model selection
prior information
error rate
closed form
conjugate priors