Efficient Online Bandit Multiclass Learning with $\tilde{O}(\sqrt{T})$ Regret

international conference on machine learning, Volume abs/1702.07958, 2017.

Cited by: 2|Views27
EI

Abstract:

We present an efficient second-order algorithm with $tilde{O}(frac{1}{eta}sqrt{T})$ regret for the bandit online multiclass problem. The regret bound holds simultaneously with respect to a family of loss functions parameterized by $eta$, for a range of $eta$ restricted by the norm of the competitor. The family of loss functions ranges fro...More

Code:

Data:

Your rating :
0

 

Tags
Comments