We study the key framework of learning with abstention in the multi-class classification setting. In this setting, the learner can choose to abstain from making a prediction with some pre-defined cost. We present a series of new theoretical and algorithmic results for this learning problem in the predictor-rejector framework. We introduce several new families of surrogate losses for which we prove strong non-asymptotic and hypothesis set-specific consistency guarantees, thereby resolving positively two existing open questions. These guarantees provide upper bounds on the estimation error of the abstention loss function in terms of that of the surrogate loss. We analyze both a single-stage setting where the predictor and rejector are learned simultaneously and a two-stage setting crucial in applications, where the predictor is learned in a first stage using a standard surrogate loss such as cross-entropy. These guarantees suggest new multi-class abstention algorithms based on minimizing these surrogate losses. We also report the results of extensive experiments comparing these algorithms to the current state-of-the-art algorithms on CIFAR-10, CIFAR-100 and SVHN datasets. Our results demonstrate empirically the benefit of our new surrogate losses and show the remarkable performance of our broadly applicable two-stage abstention algorithm.

我们研究了多类别分类中的学习与弃权的关键框架，介绍了一系列新的理论和算法结果，提出了几个新的代理损失函数家族，并分析了单阶段和两阶段学习设置的保证和应用，证明了我们的代理损失的优越性，并展示了广泛适用的两阶段弃权算法的卓越性能。

预测者-排斥者多类弃权：理论分析与算法