Unregularized online algorithms with varying Gaussians

DOI10.1007/s00365-021-09536-3zbMath1464.68321OpenAlexW3150833778MaRDI QIDQ2035494

Baobin Wang, Ting Hu

Publication date: 24 June 2021

Published in: Constructive Approximation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s00365-021-09536-3

zbMATH Keywords

reproducing kernel Hilbert spacesonline learninglearning ratevarying Gaussian kernelsgeometric noise condition

Mathematics Subject Classification ID

General nonlinear regression (62J02) Learning and adaptive systems in artificial intelligence (68T05) Hilbert spaces with reproducing kernels (= (proper) functional Hilbert spaces, including de Branges-Rovnyak and other structured spaces) (46E22) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46) Online algorithms; streaming algorithms (68W27)

Related Items

Distributed regularized least squares with flexible Gaussian kernels

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Nonparametric stochastic approximation with large step-sizes
• Multi-kernel regularized classifiers
• Fast rates for support vector machines using Gaussian kernels
• Online gradient descent learning algorithms
• Optimal aggregation of classifiers in statistical learning.
• Fully online classification by regularization
• Online learning algorithms
• Risk bounds for mixture density estimation
• On the Generalization Ability of On-Line Learning Algorithms
• An Explicit Description of the Reproducing Kernel Hilbert Spaces of Gaussian RBF Kernels
• Online Regularized Classification Algorithms
• ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY
• Minimax nonparametric classification .I. Rates of convergence
• Theory of Reproducing Kernels
• Choosing multiple parameters for support vector machines