最小化最大损失：如何以及为什么？
Minimizing the Maximal Loss: How and Why?
摘要：
常用的学习规则是近似最小化训练集上的\emph{average}损失。其他学习算法，如AdaBoost和硬SVM，旨在最小化训练集上的\emph{maximal}损失。平均损失更受欢迎，特别是在深度学习中，主要有三个原因。首先，它可以方便地最小化使用在线算法，在每次迭代处理几个例子。其次，人们经常认为，将训练集上的损失最小化太多是没有意义的，因为它不会反映在泛化损失中。最后，最大损失对异常值不鲁棒。在本文中，我们描述和分析的算法，可以将任何在线算法的最大损失的最小化。我们证明，在某些情况下，更好的准确性的训练集是至关重要的，以获得良好的性能上看不见的例子。最后，我们提出了强大的版本的方法，可以处理离群值。
英文摘要：
A commonly used learning rule is to approximately minimize the \emph{average} loss over the training set. Other learning algorithms, such as AdaBoost and hard-SVM, aim at minimizing the \emph{maximal} loss over the training set. The average loss is more popular, particularly in deep learning, due to three main reasons. First, it can be conveniently minimized using online algorithms, that process few examples at each iteration. Second, it is often argued that there is no sense to minimize the loss on the training set too much, as it will not be reflected in the generalization loss. Last, the maximal loss is not robust to outliers. In this paper we describe and analyze an algorithm that can convert any online algorithm to a minimizer of the maximal loss. We prove that in some situations better accuracy on the training set is crucial to obtain good performance on unseen examples. Last, we propose robust versions of the approach that can handle outliers.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
