On the Minimax Regret for Online Learning with Feedback Graphs.

Khaled Eldowa Emmanuel Esposito Tommaso Cesari Nicolò Cesa-Bianchi

Published in: NeurIPS (2023)

Keyphrases

online learning
minimax regret
preference elicitation
utility function
decision problems
e learning
active learning
data sets
machine learning
stochastic programming
decision makers
kernel methods
incomplete information