No-Regret Linear Bandits beyond Realizability.

Chong Liu Ming Yin Yu-Xiang Wang

Published in: UAI (2023)

Keyphrases

regret bounds
multi armed bandits
multi armed bandit
lower bound
online learning
database
case study
expert advice
loss function
linear regression
simple linear
multi armed bandit problems
convex optimization
special case
objective function
website
machine learning