English

Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case

Machine Learning 2019-06-19 v2 Machine Learning

Abstract

We study the problem of efficient online multiclass linear classification with bandit feedback, where all examples belong to one of KK classes and lie in the dd-dimensional Euclidean space. Previous works have left open the challenge of designing efficient algorithms with finite mistake bounds when the data is linearly separable by a margin γ\gamma. In this work, we take a first step towards this problem. We consider two notions of linear separability: strong and weak. 1. Under the strong linear separability condition, we design an efficient algorithm that achieves a near-optimal mistake bound of O(K/γ2)O\left( K/\gamma^2 \right). 2. Under the more challenging weak linear separability condition, we design an efficient algorithm with a mistake bound of min(2O~(Klog2(1/γ)),2O~(1/γlogK))\min (2^{\widetilde{O}(K \log^2 (1/\gamma))}, 2^{\widetilde{O}(\sqrt{1/\gamma} \log K)}). Our algorithm is based on kernel Perceptron, which is inspired by the work of (Klivans and Servedio, 2008) on improperly learning intersection of halfspaces.

Keywords

Cite

@article{arxiv.1902.02244,
  title  = {Bandit Multiclass Linear Classification: Efficient Algorithms for the Separable Case},
  author = {Alina Beygelzimer and Dávid Pál and Balázs Szörényi and Devanathan Thiruvenkatachari and Chen-Yu Wei and Chicheng Zhang},
  journal= {arXiv preprint arXiv:1902.02244},
  year   = {2019}
}

Comments

41 pages, 8 figures