资源分类
》 资源 》论文》? Ef?cient Online Bandit Multiclass Learning with ˜ O(√T) Regret

? Ef?cient Online Bandit Multiclass Learning with ˜ O(√T) Regret

2020-03-10 | |  45 |   36 |   0

Abstract

We present an efficient second-order algorithm with 图片.png 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 (Abernethy, J. and Rakhlin, A. An efficient bandit algorithm for 图片.pngregret in online multiclass prediction? In COLT, 2009). We test our algorithm experimentally, showing that it also performs favorably against earlier algorithms.

上一篇：Programming with a Differentiable Forth Interpreter

下一篇：Semi-Supervised Classification Based on Classification from Positive and Unlabeled Data

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...