Penalized empirical risk minimization over Besov spaces

DOI10.1214/08-EJS316zbMath1326.62157MaRDI QIDQ1952004

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

Mathematics Subject Classification ID

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

Related Items (4)

Inverse statistical learning ⋮ Adaptive Inference for the Bivariate Mean Function in Functional Data ⋮ Unnamed Item ⋮ Minimax fast rates for discriminant analysis with errors in variables

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Risk bounds for statistical learning
• Fast rates for support vector machines using Gaussian kernels
• Fast learning rates for plug-in classifiers
• Sous-dualités et noyaux (reproduisants) associés. (Subdualities and associated (reproducing) kernels)
• Density estimation by wavelet thresholding
• Optimal aggregation of classifiers in statistical learning.
• Classification with minimax fast rates for classes of Bayes rules with sparse representation
• Statistical performance of support vector machines
• On the subspaces of \(L^p\) \((p > 2)\) spanned by sequences of independent random variables
• Local Rademacher complexities
• Minimax-optimal classification with dyadic decision trees
• Orthonormal bases of compactly supported wavelets
• ESTIMATING THE APPROXIMATION ERROR IN LEARNING THEORY
• Rademacher penalties and structural risk minimization
• 10.1162/1532443041424337
• 10.1162/1532443041424319
• 10.1162/153244303321897690
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• Convexity, Classification, and Risk Bounds
• Model selection and error estimation

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