arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1610.04574stat.MLcs.AIcs.CVcs.LG
收藏

不变分类器的泛化误差

Generalization Error of Invariant Classifiers

University College London(伦敦大学学院);Tel-Aviv University(特拉维夫大学);Duke University(杜克大学)

Jure Sokolic, Raja Giryes, Guillermo Sapiro, Miguel R. D. Rodrigues

摘要:

研究了不变分类器的推广误差。特别是,我们考虑了常见的情况下,分类任务是不变的输入的某些变换,分类器被构造(或学习)是不变的这些变换。我们的方法依赖于将输入空间分解为一个基空间和一组变换的乘积。我们发现,而非不变分类器的泛化误差是成比例的输入空间的复杂性,不变分类器的泛化误差是成比例的基础空间的复杂性。我们还得到了一组充分条件的几何基础空间和一组的转换,以确保基础空间的复杂性是远远小于输入空间的复杂性。我们的分析适用于一般分类器,如卷积神经网络。我们证明了这种分类器的实验MNIST和CIFAR-10数据集的发展理论的影响。

英文摘要:

This paper studies the generalization error of invariant classifiers. In particular, we consider the common scenario where the classification task is invariant to certain transformations of the input, and that the classifier is constructed (or learned) to be invariant to these transformations. Our approach relies on factoring the input space into a product of a base space and a set of transformations. We show that whereas the generalization error of a non-invariant classifier is proportional to the complexity of the input space, the generalization error of an invariant classifier is proportional to the complexity of the base space. We also derive a set of sufficient conditions on the geometry of the base space and the set of transformations that ensure that the complexity of the base space is much smaller than the complexity of the input space. Our analysis applies to general classifiers such as convolutional neural networks. We demonstrate the implications of the developed theory for such classifiers with experiments on the MNIST and CIFAR-10 datasets.

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。

↑