Automated Spectral Kernel Learning
This work addresses the problem of limited generalization in kernel methods for complex tasks, offering a novel approach that is incremental in nature.
The authors tackled the limitation of stationary kernels in kernel methods by proposing a spectral kernel learning framework that learns input- and output-dependent kernels, achieving improved performance validated through extensive experiments.
The generalization performance of kernel methods is largely determined by the kernel, but common kernels are stationary thus input-independent and output-independent, that limits their applications on complicated tasks. In this paper, we propose a powerful and efficient spectral kernel learning framework and learned kernels are dependent on both inputs and outputs, by using non-stationary spectral kernels and flexibly learning the spectral measure from the data. Further, we derive a data-dependent generalization error bound based on Rademacher complexity, which estimates the generalization ability of the learning framework and suggests two regularization terms to improve performance. Extensive experimental results validate the effectiveness of the proposed algorithm and confirm our theoretical results.