Robust learning and generalization with support vector machines.

DOI10.1088/0305-4470/34/21/301MaRDI QIDQ2750775zbMATH OpenOpenAlexFDO

Authors Arnaud Buhot, Mirta B. Gordon

Publication date 21 October 2001

Published in Journal of Physics A: Mathematical and General (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/cond-mat/9802179

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural nets applied to problems in time-dependent statistical mechanics (82C32) Neural networks for/in biological studies, artificial life and related topics (92B20)

Abstract: We study the typical learning properties of the recently proposed Support Vectors Machines. The generalization error on linearly separable tasks, the capacity, the typical number of Support Vectors, the margin, and the robustness or noise tolerance of a class of Support Vector Machines are determined in the framework of Statistical Mechanics. The robustness is shown to be closely related to the generalization properties of these machines.

Recommendations

• Robustness and regularization of support vector machines
• Robust support vector machines for classification and computational issues
• On properties of support vector machines for pattern recognition in finite samples
• An asymptotic statistical analysis of support vector machines with soft margins
• Support-vector networks

Cited in

(14)

• Growing support vector classifiers with controlled complexity.
• Perturbation to enhance support vector machines for classification.
• Robustness and regularization of support vector machines
• scientific article; zbMATH DE number 6378061 (Why is no real title available?)
• Robust semi-supervised -support vector machines
• On the proliferation of support vectors in high dimensions*
• On properties of support vector machines for pattern recognition in finite samples
• Learning with rigorous support vector machines.
• On qualitative robustness of support vector machines
• An asymptotic statistical analysis of support vector machines with soft margins
• Robust support vector machines for classification and computational issues
• Tropical Support Vector Machines: Evaluations and Extension to Function Spaces
• Robustness verification of support vector machines
• New equivalences between interpolation and SVMs: kernels and structured features

This page was built for publication: Robust learning and generalization with support vector machines.

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2750775)