Efficient Online Bandit Multiclass Learning with Õ(√(T)) Regret

02/25/2017
by   Alina Beygelzimer, et al.
0

We present an efficient second-order algorithm with Õ(1/η√(T)) regret for the bandit online multiclass problem. The regret bound holds simultaneously with respect to a family of loss functions parameterized by η, for a range of η restricted by the norm of the competitor. The family of loss functions ranges from hinge loss (η=0) to squared hinge loss (η=1). This provides a solution to the open problem of (J. Abernethy and A. Rakhlin. An efficient bandit algorithm for √(T)-regret in online multiclass prediction? In COLT, 2009). We test our algorithm experimentally, showing that it also performs favorably against earlier algorithms.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset