论文标题
卷积光谱内核学习
Convolutional Spectral Kernel Learning
论文作者
论文摘要
最近，由于其强大的特征表示能力揭示了远程相关性和输入依赖性特征，因此非平稳光谱内核引起了很多关注。但是，非平稳光谱内核仍然是浅模型，因此它们不足以学习层次特征和局部相互依赖性。在本文中，为了获得层次结构和本地知识，我们基于反傅立叶变换构建了可解释的卷积光谱内核网络（\ texttt {cskn}），在那里我们将深层体系结构和卷积过滤器引入非平稳的光谱内核表示。此外，基于Rademacher的复杂性，我们得出了概括误差界限，并引入了两个正规化器以提高性能。结合了正规化器和随机初始化的最新进展，我们最终完成了\ texttt {cskn}的学习框架。对现实世界数据集的广泛实验验证了学习框架的有效性，并与我们的理论发现相吻合。
Recently, non-stationary spectral kernels have drawn much attention, owing to its powerful feature representation ability in revealing long-range correlations and input-dependent characteristics. However, non-stationary spectral kernels are still shallow models, thus they are deficient to learn both hierarchical features and local interdependence. In this paper, to obtain hierarchical and local knowledge, we build an interpretable convolutional spectral kernel network (\texttt{CSKN}) based on the inverse Fourier transform, where we introduce deep architectures and convolutional filters into non-stationary spectral kernel representations. Moreover, based on Rademacher complexity, we derive the generalization error bounds and introduce two regularizers to improve the performance. Combining the regularizers and recent advancements on random initialization, we finally complete the learning framework of \texttt{CSKN}. Extensive experiments results on real-world datasets validate the effectiveness of the learning framework and coincide with our theoretical findings.
