Login / Signup
Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual Bandits.
Zihan Zhang
Xiangyang Ji
Yuan Zhou
Published in:
CoRR (2021)
Keyphrases
</>
regret bounds
online algorithms
batch size
worst case
closed form
batch processing
multi armed bandit
online learning
batch mode
optimal linear
trade off
computational complexity
batch learning
minimum error