Penalized empirical risk minimization over Besov spaces

DOI10.1214/08-EJS316zbMATH Open1326.62157MaRDI QIDQ1952004FDOQ1952004

Authors: Sébastien Loustau 

Publication date: 27 May 2013

Published in: Electronic Journal of Statistics (Search for Journal in Brave)

Full work available at URL: https://projecteuclid.org/euclid.ejs/1250880017

Recommendations

• Sparsity in penalized empirical risk minimization
• The principle of penalized empirical risk in severely ill-posed problems
• Rademacher penalties and structural risk minimization
• Asymptotics in empirical risk minimization
• On concentration for (regularized) empirical risk minimization
• Empirical risk minimization for heavy-tailed losses
• Suboptimality of Penalized Empirical Risk Minimization in Classification
• The landscape of empirical risk for nonconvex losses
• Penalized Bregman divergence estimation via coordinate descent
• Empirical risk minimization as parameter choice rule for general linear regularization methods

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05) Ridge regression; shrinkage estimators (Lasso) (62J07)

Cites Work

• Density estimation by wavelet thresholding
• Orthonormal bases of compactly supported wavelets
• Title not available (Why is that?)
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Title not available (Why is that?)
• Local Rademacher complexities
• Title not available (Why is that?)
• Title not available (Why is that?)
• 10.1162/153244303321897690
• Convexity, Classification, and Risk Bounds
• Title not available (Why is that?)
• On the subspaces of \(L^p\) \((p > 2)\) spanned by sequences of independent random variables
• Optimal aggregation of classifiers in statistical learning.
• Rademacher penalties and structural risk minimization
• Title not available (Why is that?)
• 10.1162/1532443041424337
• Fast learning rates for plug-in classifiers
• Fast rates for support vector machines using Gaussian kernels
• Statistical performance of support vector machines
• ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY
• Risk bounds for statistical learning
• Model selection and error estimation
• Minimax-optimal classification with dyadic decision trees
• 10.1162/1532443041424319
• Aggregation of SVM classifiers using Sobolev spaces
• Title not available (Why is that?)
• Sous-dualités et noyaux (reproduisants) associés. (Subdualities and associated (reproducing) kernels)
• Classification with minimax fast rates for classes of Bayes rules with sparse representation

Cited In (7)

• Streaming kernel regression with provably adaptive mean, variance, and regularization
• Regularized kernel-based reconstruction in generalized Besov spaces
• Adaptive inference for the bivariate mean function in functional data
• An asymptotically minimax kernel machine
• Inverse statistical learning
• Minimax fast rates for discriminant analysis with errors in variables
• Soft and hard classification by reproducing kernel Hilbert space methods

This page was built for publication: Penalized empirical risk minimization over Besov spaces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1952004)