论文标题
内核依赖网络
Kernel Dependence Network
论文作者
论文摘要
我们提出了一种贪婪的策略，以光谱地训练深层网络进行多类分类。每个层都定义为线性权重的组成，其特征映射是高斯内核作为激活函数的特征图。在每一层中，线性权重是通过使用Hilbert Schmidt独立标准（HSIC）最大化层输出和标签之间的依赖性来学习的。通过在Stiefel歧管上限制解决方案空间，我们演示了如何在利用特征值自动找到网络的宽度和深度的同时，如何在光谱上求解我们的网络构建体（内核依赖网络或打net）。从理论上讲，我们保证存在全球最佳距离的解决方案，同时洞悉我们网络的概括能力。
We propose a greedy strategy to spectrally train a deep network for multi-class classification. Each layer is defined as a composition of linear weights with the feature map of a Gaussian kernel acting as the activation function. At each layer, the linear weights are learned by maximizing the dependence between the layer output and the labels using the Hilbert Schmidt Independence Criterion (HSIC). By constraining the solution space on the Stiefel Manifold, we demonstrate how our network construct (Kernel Dependence Network or KNet) can be solved spectrally while leveraging the eigenvalues to automatically find the width and the depth of the network. We theoretically guarantee the existence of a solution for the global optimum while providing insight into our network's ability to generalize.
