Classification with Gaussians and convex loss. II: Improving error bounds by noise conditions

DOI10.1007/s11425-010-4043-2zbMath1215.68203MaRDI QIDQ547325

Dao-Hong Xiang

Publication date: 1 July 2011

Published in: Science China. Mathematics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11425-010-4043-2

zbMATH Keywords

Sobolev space; reproducing kernel Hilbert space; binary classification; general convex loss; Tsybakov noise condition

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

Related Items

Comparison theorems on large-margin learning, Learning Rates for Classification with Gaussian Kernels, Learning rates of kernel-based robust classification, Quantitative convergence analysis of kernel based large-margin unified machines, The convergence rates of Shannon sampling learning algorithms

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Multi-kernel regularized classifiers
• Fast rates for support vector machines using Gaussian kernels
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• Optimal aggregation of classifiers in statistical learning.
• Learning Theory
• SVM Soft Margin Classifiers: Linear Programming versus Quadratic Programming
• Convexity, Classification, and Risk Bounds