Learning kernel-based halfspaces with the 0-1 loss

DOI10.1137/100806126MaRDI QIDQ3225166zbMATHOpenAlexFDO

Authors Shai Shalev-Shwartz, Ohad Shamir, Karthik Sridharan

Publication date 15 March 2012

Published in SIAM Journal on Computing (Search for Journal in Brave)

Full work available at URL https://semanticscholar.org/paper/97e45895efbdf6ded0824bab81b901ec4b9f8107

zbMATH Keywords

learning theorykernel methodslearning halfspaces

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computational learning theory (68Q32) Computational difficulty of problems (lower bounds, completeness, difficulty of approximation, etc.) (68Q17)

Recommendations

• Agnostically Learning Halfspaces
• Complexity theoretic limitations on learning halfspaces
• Learning intersections of halfspaces with a margin
• Learning Theory
• A random-sampling-based algorithm for learning intersections of halfspaces

Cited in

(8)

• Learning hurdles for sleeping experts
• Conditional gradient sliding for convex optimization
• Convergence results for neural networks via electrodynamics
• Conditional Gradient Methods for Convex Optimization with General Affine and Nonlinear Constraints
• A new central limit theorem and decomposition for Gaussian polynomials, with an application to deterministic approximate counting
• scientific article; zbMATH DE number 7306895 (Why is no real title available?)
• Efficiently learning halfspaces with Tsybakov noise
• A nonlinear kernel SVM Classifier via \(L_{0/1}\) soft-margin loss with classification performance

This page was built for publication: Learning kernel-based halfspaces with the 0-1 loss

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3225166)