论文标题
关于基于Rademacher复杂度的概括界的深度学习
On Rademacher Complexity-based Generalization Bounds for Deep Learning
论文作者
论文摘要
我们表明，基于Rademacher的复杂性框架可以在对一小部分图像类别进行分类的情况下为卷积神经网络（CNN）建立非胶合概括。一个关键的技术进步是为矢量空间之间的高维映射的新型收缩引理制定，这是专门为普通Lipschitz激活函数设计的。这些引理扩展并完善了塔格兰收缩的引理，并在更广泛的场景中。我们的Rademacher复杂性结合了Golowich等人提出的结果。用于基于Relu的深神经网络（DNNS）。此外，虽然先前利用Rademacher复杂性的作品主要集中在Relu dnns上，但我们的结果概括为更广泛的激活功能。
We show that the Rademacher complexity-based framework can establish non-vacuous generalization bounds for Convolutional Neural Networks (CNNs) in the context of classifying a small set of image classes. A key technical advancement is the formulation of novel contraction lemmas for high-dimensional mappings between vector spaces, specifically designed for general Lipschitz activation functions. These lemmas extend and refine the Talagrand contraction lemma across a broader range of scenarios. Our Rademacher complexity bound provides an enhancement over the results presented by Golowich et al. for ReLU-based Deep Neural Networks (DNNs). Moreover, while previous works utilizing Rademacher complexity have primarily focused on ReLU DNNs, our results generalize to a wider class of activation functions.
