Login / Signup
Efficient Online Bandit Multiclass Learning with $\tilde{O}(\sqrt{T})$ Regret.
Alina Beygelzimer
Francesco Orabona
Chicheng Zhang
Published in:
CoRR (2017)
Keyphrases
</>
online learning
online algorithms
worst case
lower bound
bandit problems
regret bounds
weighted majority
multiclass learning
reinforcement learning
machine learning
multi class
learning experience
multi armed bandit problems