The Fallacy of Minimizing Local Regret in the Sequential Task Setting.

Ziping Xu Kelly W. Zhang Susan A. Murphy

Published in: CoRR (2024)

Keyphrases

upper confidence bound
regret bounds
multi armed bandit
lower bound
worst case
online learning
binary classification
expert advice
real time
genetic algorithm
social networks
multiscale
active learning
upper bound
loss function
sequential data