Concentration inequalities and asymptotic results for ratio type empirical processes

DOI10.1214/009117906000000070zbMath1152.60021arXivmath/0606788OpenAlexW2059529070MaRDI QIDQ2497173

Evarist Giné M., Vladimir I. Koltchinskii

Publication date: 3 August 2006

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

Full work available at URL: https://arxiv.org/abs/math/0606788

zbMATH Keywords

classificationnonparametric regressionconcentration inequalitiesVC type classesratio limit theoremslocalized sup-normsmoment bounds for empirical processesratio type empirical processesweighted central limit theorems

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Inequalities; stochastic orderings (60E15) Strong limit theorems (60F15) Pattern recognition, speech recognition (68T10) Functional limit theorems; invariance principles (60F17)

Related Items

On least squares estimation under heteroscedastic and heavy-tailed errors, Upper functions for \(\mathbb{L}_{p}\)-norms of Gaussian random fields, Berry-Esseen bounds for Chernoff-type nonstandard asymptotics in isotonic regression, Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder), Minimax confidence intervals for the sliced Wasserstein distance, Bounding the expectation of the supremum of an empirical process over a (weak) VC-major class, Global testing against sparse alternatives in time-frequency analysis, On local \(U\)-statistic processes and the estimation of densities of functions of several sample variables, Upper functions for positive random functionals. I: General setting and Gaussian random functions, Complex sampling designs: uniform limit theorems and applications, Localization of VC classes: beyond local Rademacher complexities, Uniform concentration bounds for frequencies of rare events, Adaptive confidence sets in \(L^2\), On the minimax optimality and superiority of deep neural network learning over sparse parameter spaces, Adaptive estimation of a distribution function and its density in sup-norm loss by wavelet and spline projections, Tail index estimation, concentration and adaptivity, Rates of convergence in active learning, Mean estimation in high dimension, Optimal upper and lower bounds for the true and empirical excess risks in heteroscedastic least-squares regression, A local maximal inequality under uniform entropy, Efficient simulation-based minimum distance estimation and indirect inference, The generalization performance of ERM algorithm with strongly mixing observations, Nonparametric regression using deep neural networks with ReLU activation function, Uniform bounds for norms of sums of independent random functions, Uniform central limit theorems for kernel density estimators, On the uniform convergence of empirical norms and inner products, with application to causal inference, Extending the scope of the small-ball method, Uniform central limit theorems for the Grenander estimator, Some new asymptotic theory for least squares series: pointwise and uniform results, Cox process functional learning, A new method for estimation and model selection: \(\rho\)-estimation, Rho-estimators revisited: general theory and applications, Estimation from nonlinear observations via convex programming with application to bilinear regression, Surrogate losses in passive and active learning, On multivariate quantiles under partial orders, A high-dimensional Wilks phenomenon, Semi-supervised learning based on high density region estimation, The optimal PAC bound for intersection-closed concept classes, Approximating \(L_p\) unit balls via random sampling, Estimating a density, a hazard rate, and a transition intensity via the \(\rho\)-estimation method, Set structured global empirical risk minimizers are rate optimal in general dimensions, An exponential inequality for the distribution function of the kernel density estimator, with applications to adaptive estimation, When are epsilon-nets small?, Convergence rates of least squares regression estimators with heavy-tailed errors, Multiplier \(U\)-processes: sharp bounds and applications, Two-level monotonic multistage recommender systems, Sample selection models with monotone control functions, Generalization performance of graph-based semi-supervised classification, The Partial Linear Model in High Dimensions

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• The central limit theorem for empirical processes on Vapnik- Červonenkis classes
• The central limit theorem for weighted empirical processes indexed by sets
• Risk bounds for statistical learning
• Some limit theorems for the empirical process indexed by functions
• Weighted empirical and quantile processes
• Rates of growth and sample moduli for weighted empirical processes indexed by sets
• Limit theorems and inequalities for the uniform empirical process indexed by intervals
• Fréchet differentiability, \(p\)-variation and uniform Donsker classes
• On the weak convergence of empirical processes in sup-norm metrics
• The asymptotic distribution of the supremum of the standardized empirical distribution function on subintervals
• The asymptotic distribution of the suprema of the standardized empirical processes
• Minimum contrast estimators on sieves: Exponential bounds and rates of convergence
• Sharper bounds for Gaussian and empirical processes
• Bounds on margin distributions in learning problems
• Symmetrization approach to concentration inequalities for empirical processes.
• A Bennett concentration inequality and its application to suprema of empirical processes
• Empirical margin distributions and bounding the generalization error of combined classifiers
• Some extensions of an inequality of Vapnik and Chervonenkis
• 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
• An inequality for uniform deviations of sample averages from their means
• Hellinger-consistency of certain nonparametric maximum likelihood estimators
• Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
• The law of the iterated logarithm for normalized empirical distribution function
• Limit theorems for the ratio of the empirical distribution function to the true distribution function
• Uniform Central Limit Theorems
• Extension to higher dimensions of the jaeschke-eicker result on the standardized empirical process
• Strong limit theorems for oscillation moduli of the uniform empirical process
• 10.1162/153244303321897690
• Convergence of stochastic processes
• An empirical process approach to the uniform consistency of kernel-type function estimators
• Some applications of concentration inequalities to statistics
• On consistency of kernel density estimators for randomly censored data: Rates holding uniformly over adaptive intervals
• New concentration inequalities in product spaces