A high-dimensional Wilks phenomenon

DOI10.1007/s00440-010-0278-7zbMath1230.62072OpenAlexW1980421881WikidataQ58374458 ScholiaQ58374458MaRDI QIDQ718891

Pascal Massart, Stéphane Boucheron

Publication date: 27 September 2011

Published in: Probability Theory and Related Fields (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s00440-010-0278-7

zbMATH Keywords

concentration inequalitiesstatistical learningsuprema of empirical processesrisk estimates

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Inequalities; stochastic orderings (60E15) Nonparametric inference (62G99)

Related Items

Finite sample Bernstein-von Mises theorem for semiparametric problems, Sharp deviation bounds for quadratic forms, On concentration for (regularized) empirical risk minimization, Discussion of ``On concentration for (regularized) empirical risk minimization by Sara van de Geer and Martin Wainwright, On accuracy of Gaussian approximation in Bayesian semiparametric problems, Model selection: from theory to practice, Optimal upper and lower bounds for the true and empirical excess risks in heteroscedastic least-squares regression, Optimal model selection in heteroscedastic regression using piecewise polynomial functions, A conversation with Jon Wellner, Critical dimension in profile semiparametric estimation, Critical dimension in the semiparametric Bernstein-von Mises theorem, The likelihood ratio test in high-dimensional logistic regression is asymptotically a rescaled Chi-square, One-Step Estimation with Scaled Proximal Methods

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Risk bounds for statistical learning
• Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
• Rates of growth and sample moduli for weighted empirical processes indexed by sets
• Asymptotic behavior of likelihood methods for exponential families when the number of parameters tends to infinity
• The jackknife estimate of variance
• Smooth discrimination analysis
• A Bennett concentration inequality and its application to suprema of empirical processes
• Moment inequalities for functions of independent random variables
• Density and dimension
• Generalized likelihood ratio statistics and Wilks phenomenon
• Minimax testing composite null hypotheses in the discrete regression scheme
• About the constants in Talagrand's concentration inequalities for empirical processes.
• Optimal aggregation of classifiers in statistical learning.
• Weak convergence and empirical processes. With applications to statistics
• A new look at independence
• Local linear regression smoothers and their minimax efficiencies
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Empirical minimization
• Concentration inequalities and asymptotic results for ratio type empirical processes
• On Talagrand's deviation inequalities for product measures
• Theory of Classification: a Survey of Some Recent Advances
• Distribution-free inequalities for the deleted and holdout error estimates
• Asymptotic Statistics
• Some Comments on C P
• STABILITY RESULTS IN LEARNING THEORY
• The Large-Sample Distribution of the Likelihood Ratio for Testing Composite Hypotheses
• Convergence of stochastic processes
• Some applications of concentration inequalities to statistics
• Concentration inequalities for set-indexed empirical processes
• Model selection and error estimation
• New concentration inequalities in product spaces
• A new look at the statistical model identification