Truncated Kernel Stochastic Gradient Descent with General Losses and Spherical Radial Basis Functions
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913060790206464 |
|---|---|
| author | Bai, Jinhui Christmann, Andreas Shi, Lei |
| author_facet | Bai, Jinhui Christmann, Andreas Shi, Lei |
| contents | In this paper, we propose a novel kernel stochastic gradient descent (SGD) algorithm for large-scale supervised learning with general losses. Compared to traditional kernel SGD, our algorithm improves efficiency and scalability through an innovative regularization strategy. By leveraging the infinite series expansion of spherical radial basis functions, this strategy projects the stochastic gradient onto a finite-dimensional hypothesis space, which is adaptively scaled according to the bias-variance trade-off, thereby enhancing generalization performance. Based on a new estimation of the spectral structure of the kernel-induced covariance operator, we develop an analytical framework that unifies optimization and generalization analyses. We prove that both the last iterate and the suffix average converge at minimax-optimal rates, and we further establish optimal strong convergence in the reproducing kernel Hilbert space. Our framework accommodates a broad class of classical loss functions, including least-squares, Huber, and logistic losses. Moreover, the proposed algorithm significantly reduces computational complexity and achieves optimal storage complexity by incorporating coordinate-wise updates from linear SGD, thereby avoiding the costly pairwise operations typical of kernel SGD and enabling efficient processing of streaming data. Finally, extensive numerical experiments demonstrate the efficiency of our approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_04237 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Truncated Kernel Stochastic Gradient Descent with General Losses and Spherical Radial Basis Functions Bai, Jinhui Christmann, Andreas Shi, Lei Machine Learning 68T05, 68Q32, 62L20 In this paper, we propose a novel kernel stochastic gradient descent (SGD) algorithm for large-scale supervised learning with general losses. Compared to traditional kernel SGD, our algorithm improves efficiency and scalability through an innovative regularization strategy. By leveraging the infinite series expansion of spherical radial basis functions, this strategy projects the stochastic gradient onto a finite-dimensional hypothesis space, which is adaptively scaled according to the bias-variance trade-off, thereby enhancing generalization performance. Based on a new estimation of the spectral structure of the kernel-induced covariance operator, we develop an analytical framework that unifies optimization and generalization analyses. We prove that both the last iterate and the suffix average converge at minimax-optimal rates, and we further establish optimal strong convergence in the reproducing kernel Hilbert space. Our framework accommodates a broad class of classical loss functions, including least-squares, Huber, and logistic losses. Moreover, the proposed algorithm significantly reduces computational complexity and achieves optimal storage complexity by incorporating coordinate-wise updates from linear SGD, thereby avoiding the costly pairwise operations typical of kernel SGD and enabling efficient processing of streaming data. Finally, extensive numerical experiments demonstrate the efficiency of our approach. |
| title | Truncated Kernel Stochastic Gradient Descent with General Losses and Spherical Radial Basis Functions |
| topic | Machine Learning 68T05, 68Q32, 62L20 |
| url | https://arxiv.org/abs/2510.04237 |