Nearly Optimal Regret for Stochastic Linear Bandits with Heavy-Tailed Payoffs.

Bo Xue Guanghui Wang Yimu Wang Lijun Zhang

Published in: IJCAI (2020)

Keyphrases

regret bounds
heavy tailed
lower bound
online learning
multi armed bandit
linear regression
upper bound
worst case
generalized gaussian
closed form
bregman divergences
image processing
bayesian networks
denoising
heavy tails