A Bernstein-type inequality for suprema of random processes with applications to model selection in non-Gaussian regression

DOI10.3150/09-BEJ245zbMath1459.60044arXiv0909.1863MaRDI QIDQ627287

Yannick Baraud

Publication date: 28 February 2011

Published in: Bernoulli (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/0909.1863

zbMATH Keywords

model selectionregressionBernstein's inequalitysupremum of a random process

Mathematics Subject Classification ID

Ridge regression; shrinkage estimators (Lasso) (62J07) Inequalities; stochastic orderings (60E15) Extreme value theory; extremal stochastic processes (60G70) Diagnostics, and linear inference and regression (62J20) Limit theorems in probability theory (60F99)

Related Items

Concentration inequalities, counting processes and adaptive statistics, Spectral estimation for diffusions with random sampling times, Unnamed Item, Sharp deviation bounds for quadratic forms, A Bernstein-type inequality for suprema of random processes with applications to model selection in non-Gaussian regression, Adaptive estimation of the conditional intensity of marker-dependent counting processes, Local M-estimation with discontinuous criterion for dependent and limited observations, On Hoeffding and Bernstein type inequalities for sums of random variables in non-additive measure spaces and complete convergence, Weighted stochastic block model, Concentration of scalar ergodic diffusions and some statistical implications, Nonparametric Bayesian posterior contraction rates for scalar diffusions with high-frequency data, Adaptive invariant density estimation for continuous-time mixing Markov processes under sup-norm risk, Adaptive estimation of the baseline hazard function in the Cox model by model selection, with high-dimensional covariates

Cites Work

• Unnamed Item
• A Bernstein-type inequality for suprema of random processes with applications to model selection in non-Gaussian regression
• Concentration inequalities and model selection. Ecole d'Eté de Probabilités de Saint-Flour XXXIII -- 2003.
• Risk bounds for model selection via penalization
• Model selection for regression on a fixed design
• A Bennett concentration inequality and its application to suprema of empirical processes
• Concentration around the mean for maxima of empirical processes
• Une inégalité de Bennett pour les maxima de processus empiriques. (A Bennet type inequality for maxima of empirical processes)
• About the constants in Talagrand's concentration inequalities for empirical processes.
• Concentration of measure and isoperimetric inequalities in product spaces
• On weakly bounded empirical processes
• Reconstruction and subgaussian operators in asymptotic geometric analysis
• Empirical processes and random projections
• On Talagrand's deviation inequalities for product measures
• Minimum complexity density estimation
• Model selection for (auto-)regression with dependent data
• The Generic Chaining
• [https://portal.mardi4nfdi.de/wiki/Publication:4743580 Approximation dans les espaces m�triques et th�orie de l'estimation]
• Histogram selection in non Gaussian regression
• Gaussian model selection