Login / Signup
Optimal Algorithms for Online Convex Optimization with Multi-Point Bandit Feedback.
Alekh Agarwal
Ofer Dekel
Lin Xiao
Published in:
COLT (2010)
Keyphrases
</>
worst case
optimization problems
online convex optimization
learning algorithm
dynamic programming
newton method
optimal solution
principal component analysis
online learning
regret bounds