COLT 2011 - Accepted Open Problems

Elad Hazan and Satyen Kale:
A simple multi-armed bandit algorithm with optimal variation-bounded regret.

Jacob Abernethy and Shie Mannor:
Does an efficient calibrated forecasting strategy exist?
 
Aleksandrs Slivkins:
Monotone multi-armed bandit allocations.

Peter Grünwald and Wojciech Kotłowski:
Bounds on individual risk for log-loss predictors.

Wojciech Kotłowski and Manfred Warmuth:  
Minimax algorithm for learning rotations.

Loizos Michael:  
Missing information impediments to learnability.