论文标题
Minimax风险分类器，损失为0-1
Minimax risk classifiers with 0-1 loss
论文作者
论文摘要
有监督的分类技术使用培训样本来学习一个预期0-1损失（错误概率）的分类规则。常规方法可以通过使用替代损失而不是0-1损失并考虑特定的规则家族（假设类别）来实现可拖动学习并提供样本外的概括。本文介绍了最小风险分类器（MRC），这些分布量降低了最坏情况下的0-1损失，但对于不确定性的分布组，可以包含基础分布，并具有可调的置信度。我们表明，MRC可以在学习方面提供紧张的性能保证，并且使用特征内核给出的功能映射非常普遍。本文还提出了有效的MRC学习优化技术，并表明所提出的方法可以提供准确的分类以及实践中的紧张性能保证。
Supervised classification techniques use training samples to learn a classification rule with small expected 0-1 loss (error probability). Conventional methods enable tractable learning and provide out-of-sample generalization by using surrogate losses instead of the 0-1 loss and considering specific families of rules (hypothesis classes). This paper presents minimax risk classifiers (MRCs) that minize the worst-case 0-1 loss with respect to uncertainty sets of distributions that can include the underlying distribution, with a tunable confidence. We show that MRCs can provide tight performance guarantees at learning and are strongly universally consistent using feature mappings given by characteristic kernels. The paper also proposes efficient optimization techniques for MRC learning and shows that the methods presented can provide accurate classification together with tight performance guarantees in practice.
