Consistency of learning algorithms using Attouch-Wets convergence

DOI10.1080/02331934.2010.511671zbMATH Open1236.93157OpenAlexW1992153994MaRDI QIDQ3225085FDOQ3225085

Authors: Silvia Villa, Lorenzo Rosasco, Sofia Mosci, Alessandro Verri 

Publication date: 15 March 2012

Published in: Optimization (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/02331934.2010.511671

Recommendations

• Learnability, stability and uniform convergence
• On regularization algorithms in learning theory
• Learning theory: stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk minimization
• Iterative regularization for learning with convex loss functions
• A survey on learning theory. I: Stability and generalization

zbMATH Keywords

Attouch-Wets convergencestatistical learning theoryTikhonov well-posedness

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computational learning theory (68Q32) Sensitivity, stability, well-posedness (49K40) Numerical solutions of ill-posed problems in abstract spaces; regularization (65J20) Stochastic learning and adaptive control (93E35)

Cites Work

• Learning Theory
• On the mathematical foundations of learning
• A Statistical View of Some Chemometrics Regression Tools
• Title not available (Why is that?)
• An iterative algorithm for nonlinear inverse problems with joint sparsity constraints in vector-valued regimes and an application to color image inpainting
• Quantitative Stability of Variational Systems: I. The Epigraphical Distance
• Title not available (Why is that?)
• Theory of Classification: a Survey of Some Recent Advances
• Fast rates for support vector machines using Gaussian kernels
• Model selection for regularized least-squares algorithm in learning theory
• Epigraphical and Uniform Convergence of Convex Functions
• Stability of $\varepsilon$-approximate Solutions to Convex Stochastic Programs
• Quantitative Stability of Variational Systems II. A Framework for Nonlinear Conditioning
• Networks and the best approximation property
• A dynamical approach to convex minimization coupling approximation with the steepest descent method
• Quantitative stability of variational systems. III: \(\varepsilon\)- approximate solutions

Cited In (1)

• Learning sparse conditional distribution: an efficient kernel-based approach

This page was built for publication: Consistency of learning algorithms using Attouch-Wets convergence

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3225085)