Learning Analysis of Kernel Ridgeless Regression with Asymmetric Kernel Learning
He, Fan, He, Mingzhen, Shi, Lei, Huang, Xiaolin, Suykens, Johan A. K.
Ridgeless regression has garnered attention among researchers, particularly in light of the ``Benign Overfitting'' phenomenon, where models interpolating noisy samples demonstrate robust generalization. However, kernel ridgeless regression does not always perform well due to the lack of flexibility. This paper enhances kernel ridgeless regression with Locally-Adaptive-Bandwidths (LAB) RBF kernels, incorporating kernel learning techniques to improve performance in both experiments and theory. For the first time, we demonstrate that functions learned from LAB RBF kernels belong to an integral space of Reproducible Kernel Hilbert Spaces (RKHSs). Despite the absence of explicit regularization in the proposed model, its optimization is equivalent to solving an $\ell_0$-regularized problem in the integral space of RKHSs, elucidating the origin of its generalization ability. Taking an approximation analysis viewpoint, we introduce an $l_q$-norm analysis technique (with $0
Jun-3-2024
- Country:
- Europe (0.67)
- North America
- Canada > Ontario
- Toronto (0.14)
- United States (0.28)
- Canada > Ontario
- Genre:
- Research Report > New Finding (0.92)
- Technology: