标题： 半监督学习中分类的插件置信集的一致性 显示英文标题

标题： Consistency of plug-in confidence sets for classification in semi-supervised learning

摘要： 置信预测在机器学习中非常重要；例如，在医疗诊断等应用中，错误的预测可能会致命。 对于分类，已经存在允许在预测置信度较弱时不对数据进行分类的程序。 这种方法被称为带有拒绝选项的分类。 在本文中，我们为此方法提供了新的方法论。 通过置信集预测新实例，我们确保对分类概率的精确控制。 此外，我们表明这种方法易于实现，并具有吸引人的理论和数值特性。 显示英文摘要

摘要： Confident prediction is highly relevant in machine learning; for example, in applications such as medical diagnoses, wrong prediction can be fatal. For classification, there already exist procedures that allow to not classify data when the confidence in their prediction is weak. This approach is known as classification with reject option. In the present paper, we provide new methodology for this approach. Predicting a new instance via a confidence set, we ensure an exact control of the probability of classification. Moreover, we show that this methodology is easily implementable and entails attractive theoretical and numerical properties.