Login / Signup
Minimax Optimal Quantile and Semi-Adversarial Regret via Root-Logarithmic Regularizers.
Jeffrey Negrea
Blair L. Bilodeau
Nicolò Campolongo
Francesco Orabona
Dan Roy
Published in:
NeurIPS (2021)
Keyphrases
</>
worst case
regret bounds
lower bound
minimax regret
online learning
multi agent
dynamic programming
upper bound
tree structure
optimal control
image processing
loss function
closed form
asymptotically optimal