Bandits with Side Observations: Bounded vs. Logarithmic Regret.

Rémy Degenne Evrard Garcelon Vianney Perchet

Published in: UAI (2018)

Keyphrases

regret bounds
lower bound
linear regression
multi armed bandit
online learning
expert advice
upper bound
worst case
multi armed bandit problems
bregman divergences
online convex optimization
multi armed bandits
binary classification
least squares
multi agent systems
case study
information retrieval
real time