A Bennett concentration inequality and its application to suprema of empirical processes

DOI10.1016/S1631-073X(02)02292-6zbMATH Open1001.60021MaRDI QIDQ1600147FDOQ1600147

Authors: Olivier Bousquet 

Publication date: 15 December 2002

Published in: Comptes Rendus. Mathématique. Académie des Sciences, Paris (Search for Journal in Brave)

Recommendations

• Concentration inequalities for suprema of unbounded empirical processes
• New concentration inequalities for suprema of empirical processes
• About the rate function in concentration inequalities for suprema of bounded empirical processes
• Comparison inequalities for suprema of bounded empirical processes
• scientific article; zbMATH DE number 4048767
• Concentration inequalities for set-indexed empirical processes
• Estimates of the supremum distribution for a certain class of random processes
• Bounding the expectation of the supremum of empirical processes indexed by Hölder classes

zbMATH Keywords

concentration inequalitiessuprema of empirical processesBennett type deviation bound

Mathematics Subject Classification ID

Inequalities; stochastic orderings (60E15)

Cites Work

• Concentration inequalities. A nonasymptotic theory of independence
• New concentration inequalities in product spaces
• About the constants in Talagrand's concentration inequalities for empirical processes.
• On Talagrand's deviation inequalities for product measures
• A sharp concentration inequality with applications
• Concentration inequalities for set-indexed empirical processes

Cited In (only showing first 100 items - show all)

• Sharp large deviation results for sums of independent random variables
• Bounding the expectation of the supremum of empirical processes indexed by Hölder classes
• Upper functions for \(\mathbb{L}_{p}\)-norms of Gaussian random fields
• A reproducing kernel Hilbert space approach to high dimensional partially varying coefficient model
• Upper functions for positive random functionals. I: General setting and Gaussian random functions
• Fast learning rate of non-sparse multiple kernel learning and optimal regularization strategies
• A Bernstein-type inequality for suprema of random processes with applications to model selection in non-Gaussian regression
• About the rate function in Talagrand's inequality for empirical processes
• Uniform bounds for norms of sums of independent random functions
• Une inégalité de Bennett pour les maxima de processus empiriques. (A Bennet type inequality for maxima of empirical processes)
• Thermodynamics and concentration
• Optimal model selection in density estimation
• High-dimensional generalized linear models and the lasso
• Adaptive density estimation on bounded domains
• Oracle inequalities for sparse additive quantile regression in reproducing kernel Hilbert space
• Partitioning a macroscopic system into independent subsystems
• A limited in bandwidth uniformity for the functional limit law of the increments of the empirical process
• A high-dimensional Wilks phenomenon
• On higher order isotropy conditions and lower bounds for sparse quadratic forms
• Concentration inequalities using the entropy method
• Estimation of Censored Quantile Regression for Panel Data With Fixed Effects
• Characterization of LIL behavior in Banach space
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• Blockwise SVD with error in the operator and application to blind deconvolution
• Learning performance of regularized moving least square regression
• Adaptive density estimation of stationary \(\beta\)-mixing and \(\tau\)-mixing processes
• Local Rademacher complexities
• Forward regression for Cox models with high-dimensional covariates
• Model selection: from theory to practice
• Hoeffding's inequality for supermartingales
• Compensator and exponential inequalities for some suprema of counting processes
• Concentration around the mean for maxima of empirical processes
• Fast rates for support vector machines using Gaussian kernels
• Adaptive sup-norm estimation of the Wigner function in noisy quantum homodyne tomography
• Stability and minimax optimality of tangential Delaunay complexes for manifold reconstruction
• Complexity regularization via localized random penalties
• Moment inequalities for functions of independent random variables
• About the rate function in concentration inequalities for suprema of bounded empirical processes
• Symmetrization approach to concentration inequalities for empirical processes.
• Nonparametric estimation of low rank matrix valued function
• Concentration inequalities and asymptotic results for ratio type empirical processes
• U-Processes and Preference Learning
• Statistical properties of kernel principal component analysis
• On the Bennett-Hoeffding inequality
• Interpolation via weighted \(\ell_{1}\) minimization
• Fast rates for empirical vector quantization
• Empirical risk minimization is optimal for the convex aggregation problem
• Local Rademacher complexity: sharper risk bounds with and without unlabeled samples
• General oracle inequalities for model selection
• Concentration inequalities for functions of independent variables
• High-dimensional additive modeling
• Inverse statistical learning
• New concentration inequalities for suprema of empirical processes
• On G. Bennett's inequality
• Asymptotics for panel quantile regression models with individual effects
• Optimal model selection for density estimation of stationary data under various mixing condi\-tions
• Statistical performance of support vector machines
• Risk bounds for statistical learning
• Direct importance estimation for covariate shift adaptation
• Uniform convergence rate of the kernel regression estimator adaptive to intrinsic dimension in presence of censored data
• Concentration inequalities for suprema of unbounded empirical processes
• The Bernstein-Orlicz norm and deviation inequalities
• Classification with non-i.i.d. sampling
• Sparsity in multiple kernel learning
• Variance-based regularization with convex objectives
• Uniform in bandwidth exact rates for a class of kernel estimators
• Theory of Classification: a Survey of Some Recent Advances
• Robust group synchronization via cycle-edge message passing
• An oracle approach for interaction neighborhood estimation in random fields
• Concentration inequalities for empirical processes of linear time series
• Concentration inequalities, counting processes and adaptive statistics
• Convergence rates for the generalized Fréchet mean via the quadruple inequality
• High dimensional generalized linear models for temporal dependent data
• On polynomial time methods for exact low-rank tensor completion
• Convergence rates for empirical barycenters in metric spaces: curvature, convexity and extendable geodesics
• The shattering dimension of sets of linear functionals.
• Local Rademacher complexity-based learning guarantees for multi-task learning
• Robust matrix estimations meet Frank-Wolfe algorithm
• Measuring the capacity of sets of functions in the analysis of ERM
• Collective matrix completion
• An improved Bennett's inequality
• Improving Hoeffding's inequality using higher moments information
• Sparse recovery in bounded Riesz systems with applications to numerical methods for PDEs
• Sparse quantile regression
• Nearly optimal robust mean estimation via empirical characteristic function
• Concentration inequalities for bounded functionals via log-Sobolev-type inequalities
• On the geometry of polytopes generated by heavy-tailed random vectors
• Learning with convex loss and indefinite kernels
• Sharp oracle inequalities and slope heuristic for specification probabilities estimation in discrete random fields
• Nearest neighbor empirical processes
• High-dimensional local linear regression under sparsity and convex losses
• Title not available (Why is that?)
• Bandwidth selection in kernel empirical risk minimization via the gradient
• Post-regularization inference for time-varying nonparanormal graphical models
• The Bennett-Orlicz norm
• Kernel meets sieve: post-regularization confidence bands for sparse additive model
• Modified log-Sobolev inequalities, Beckner inequalities and moment estimates
• Optimal upper and lower bounds for the true and empirical excess risks in heteroscedastic least-squares regression
• Learning rates for partially linear functional models with high dimensional scalar covariates
• Moving quantile regression

This page was built for publication: A Bennett concentration inequality and its application to suprema of empirical processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1600147)