Bandwidth selection in kernel empirical risk minimization via the gradient

DOI10.1214/15-AOS1318zbMath1317.62026arXiv1401.6882MaRDI QIDQ2515491

Michaël Chichignoud, Sébastien Loustau

Publication date: 5 August 2015

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1401.6882

zbMATH Keywords

adaptivitybandwidth selectionerrors-in-variablesrobust regressionstatistical learningERM

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Asymptotic properties of nonparametric inference (62G20) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Nonparametric estimation (62G05)

Related Items (1)

Local bandwidth selection for kernel density estimation in a bifurcating Markov chain model

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Fast rates for empirical vector quantization
• Inverse statistical learning
• A robust, adaptive M-estimator for pointwise estimation in heteroscedastic regression
• Bandwidth selection in kernel density estimation: oracle inequalities and adaptive minimax optimality
• Uniform bounds for norms of sums of independent random functions
• From local kernel to nonlocal multiple-model image denoising
• Risk bounds for statistical learning
• Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
• On density estimation in the view of Kolmogorov's ideas in approximation theory
• Estimation of distributions, moments and quantiles in deconvolution problems
• Structural adaptation via \(\mathbb L_p\)-norm oracle inequalities
• Universal pointwise selection rule in multivariate function estimation
• Strong consistency of k-means clustering
• A central limit theorem for k-means clustering
• Optimal spatial adaptation to inhomogeneous smoothness: An approach based on kernel estimates with variable bandwidth selectors
• Smooth discrimination analysis
• A Bennett concentration inequality and its application to suprema of empirical processes
• Optimal aggregation of classifiers in statistical learning.
• Anisotropic adaptive kernel deconvolution
• Pointwise adaptive estimation of a multivariate function
• Minimax fast rates for discriminant analysis with errors in variables
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Statistical performance of support vector machines
• Simultaneous adaptation to the margin and to complexity in classification
• Propagation-separation approach for local likelihood estimation
• Theory of uniform convergence of frequencies of events to their probabilities and problems of search for an optimal solution from empirical data
• Adaptive Noisy Clustering
• Theory of Classification: a Survey of Some Recent Advances
• Individual Convergence Rates in Empirical Vector Quantizer Design
• Spatially Adaptive Estimation via Fitted Local Likelihood Techniques
• On a Problem of Adaptive Estimation in Gaussian White Noise
• 10.1162/1532443041424337
• Oracle Inequalities and Minimax Rates for Nonlocal Means and Related Adaptive Kernel-Based Methods
• Robust Estimation of a Location Parameter
• Introduction to nonparametric estimation
• Nonlinear estimation in anisotropic multi-index denoising
• New concentration inequalities in product spaces
• Adaptive quantile estimation in deconvolution with unknown error distribution

This page was built for publication: Bandwidth selection in kernel empirical risk minimization via the gradient