Bandits with Side Observations: Bounded vs. Logarithmic Regret.

Rémy Degenne Evrard Garcelon Vianney Perchet

Published in: CoRR (2018)

Keyphrases

regret bounds
online learning
lower bound
expert advice
linear regression
multi armed bandit
worst case
upper bound
bregman divergences
multi armed bandits
machine learning
artificial intelligence
information systems
loss bounds
bandit problems
multi armed bandit problems