Login / Signup
A Stochastic View of Optimal Regret through Minimax Duality.
Jacob D. Abernethy
Alekh Agarwal
Peter L. Bartlett
Alexander Rakhlin
Published in:
COLT (2009)
Keyphrases
</>
worst case
minimax regret
regret bounds
online learning
optimal solution
multi armed bandit
closed form
linear programming
multiple views
locally optimal
lower bound
markov chain
loss function
dynamic programming
total cost
preference elicitation
search algorithm
e learning