On the Minimax Regret for Online Learning with Feedback Graphs.

Khaled Eldowa Emmanuel Esposito Tommaso Cesari Nicolò Cesa-Bianchi

Published in: CoRR (2023)

Keyphrases

markov chain
online learning
minimax regret
preference elicitation
e learning
utility function
decision problems
active learning
stochastic programming
optimization criterion
cost sensitive
misclassification costs
robust optimization