Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)

DOI10.1214/009053606000001019MaRDI QIDQ2373576zbMATH OpenOpenAlexWikidataFDO

Authors Vladimir Koltchinskii

Publication date 12 July 2007

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

Full work available at URL https://arxiv.org/abs/0708.0083

zbMATH Keywords

classificationconcentration inequalitiesempirical risk minimizationmodel selection

Mathematics Subject Classification ID

Probability theory on algebraic and topological structures (60B99) Nonparametric regression and quantile regression (62G08) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10)

Abstract: Let $mathcalF$ be a class of measurable functions $f:Smapsto[0,1]$ defined on a probability space $(S,mathcalA,P)$. Given a sample (X_1,...,X_n) of i.i.d. random variables taking values in S with common distribution P, let P_n denote the empirical measure based on (X_1,...,X_n). We study an empirical risk minimization problem $P_{n}fomin$, $finmathcalF$. Given a solution $hat{f}_n$ of this problem, the goal is to obtain very general upper bounds on its excess risk [mathcal{E}_P(hat{f}_n):=Phat{f}_n-inf_{fin mathcal{F}}Pf,] expressed in terms of relevant geometric parameters of the class $mathcalF$. Using concentration inequalities and other empirical processes tools, we obtain both distribution-dependent and data-dependent upper bounds on the excess risk that are of asymptotically correct order in many examples. The bounds involve localized sup-norms of empirical and Rademacher processes indexed by functions from the class. We use these bounds to develop model selection techniques in abstract risk minimization problems that can be applied to more specialized frameworks of regression and classification.

Recommendations

• scientific article; zbMATH DE number 1552503
• Local Rademacher complexities
• Learning Theory
• 10.1162/153244303321897690
• Risk bounds for statistical learning

Cites work

• 10.1162/1532443041424319
• A Bennett concentration inequality and its application to suprema of empirical processes
• A distribution-free theory of nonparametric regression
• A new look at independence
• A sharp concentration inequality with applications
• An empirical process approach to the uniform consistency of kernel-type function estimators
• Bounding the generalization error of convex combinations of classifiers: Balancing the dimensionality and the margins.
• Complexities of convex combinations and bounding the generalization error in classification
• Complexity regularization via localized random penalties
• Concentration inequalities and asymptotic results for ratio type empirical processes
• Consistency of Support Vector Machines and Other Regularized Kernel Classifiers
• Convergence rate of sieve estimates
• Convexity, Classification, and Risk Bounds
• Efficient agnostic learning of neural networks with bounded fan-in
• Empirical margin distributions and bounding the generalization error of combined classifiers
• Empirical minimization
• scientific article; zbMATH DE number 2089352 (Why is no real title available?)
• scientific article; zbMATH DE number 2089354 (Why is no real title available?)
• scientific article; zbMATH DE number 5654889 (Why is no real title available?)
• scientific article; zbMATH DE number 49190 (Why is no real title available?)
• scientific article; zbMATH DE number 1332320 (Why is no real title available?)
• scientific article; zbMATH DE number 1064642 (Why is no real title available?)
• scientific article; zbMATH DE number 2034518 (Why is no real title available?)
• scientific article; zbMATH DE number 1552503 (Why is no real title available?)
• scientific article; zbMATH DE number 3446442 (Why is no real title available?)
• scientific article; zbMATH DE number 893887 (Why is no real title available?)
• Improving the sample complexity using global data
• Inequalities for uniform deviations of averages from expectations with applications to nonparametric regression
• Left concentration inequalities for empirical processes
• Local Rademacher complexities
• Model selection and error estimation
• Model selection for regression on a random design
• Moment inequalities for functions of independent random variables
• Neural Network Learning
• New concentration inequalities in product spaces
• On consistency of kernel density estimators for randomly censored data: Rates holding uniformly over adaptive intervals
• On the Bayes-risk consistency of regularized boosting methods.
• Optimal aggregation of classifiers in statistical learning.
• Oracle inequalities and nonparametric function estimation
• Rademacher penalties and structural risk minimization
• Risk bounds for model selection via penalization
• Sharper bounds for Gaussian and empirical processes
• Smooth discrimination analysis
• Some applications of concentration inequalities to statistics
• Some limit theorems for empirical processes (with discussion)
• Square root penalty: Adaption to the margin in classification and in edge estimation
• Statistical behavior and consistency of classification methods based on convex risk minimization.
• Statistical performance of support vector machines
• Uniform Central Limit Theorems
• Weak convergence and empirical processes. With applications to statistics

Cited in

(only showing first 100 items - show all)

• A universal procedure for aggregating estimators
• Sparse recovery in convex hulls via entropy penalization
• Direct importance estimation for covariate shift adaptation
• Measuring distributional asymmetry with Wasserstein distance and Rademacher symmetrization
• Fast learning rate of non-sparse multiple kernel learning and optimal regularization strategies
• Joint regression analysis of mixed-type outcome data via efficient scores
• Local Rademacher complexity: sharper risk bounds with and without unlabeled samples
• On concentration for (regularized) empirical risk minimization
• Discussion of ``On concentration for (regularized) empirical risk minimization by Sara van de Geer and Martin Wainwright
• Relative deviation learning bounds and generalization with unbounded loss functions
• Bayesian fractional posteriors
• Robust multicategory support vector machines using difference convex algorithm
• Mass volume curves and anomaly ranking
• Complexity regularization via localized random penalties
• On the optimality of the empirical risk minimization procedure for the convex aggregation problem
• Optimal upper and lower bounds for the true and empirical excess risks in heteroscedastic least-squares regression
• Oracle inequalities for cross-validation type procedures
• Optimal model selection in heteroscedastic regression using piecewise polynomial functions
• General oracle inequalities for model selection
• Model selection by resampling penalization
• On the optimality of the aggregate with exponential weights for low temperatures
• Adaptive kernel methods using the balancing principle
• Rho-estimators revisited: general theory and applications
• Singularity, misspecification and the convergence rate of EM
• Surrogate losses in passive and active learning
• Tests and estimation strategies associated to some loss functions
• Set structured global empirical risk minimizers are rate optimal in general dimensions
• Fast generalization error bound of deep learning without scale invariance of activation functions
• Multiplier \(U\)-processes: sharp bounds and applications
• Optimal linear discriminators for the discrete choice model in growing dimensions
• An elementary analysis of ridge regression with random design
• Suboptimality of constrained least squares and improvements via non-linear predictors
• A no-free-lunch theorem for multitask learning
• On least squares estimation under heteroscedastic and heavy-tailed errors
• Empirical variance minimization with applications in variance reduction and optimal control
• Optimal robust mean and location estimation via convex programs with respect to any pseudo-norms
• Robust statistical learning with Lipschitz and convex loss functions
• Convergence rates for empirical barycenters in metric spaces: curvature, convexity and extendable geodesics
• On the minimax optimality and superiority of deep neural network learning over sparse parameter spaces
• Aggregation of estimators and stochastic optimization
• From Gauss to Kolmogorov: localized measures of complexity for ellipses
• ERM and RERM are optimal estimators for regression problems when malicious outliers corrupt the labels
• Nonparametric regression using deep neural networks with ReLU activation function
• Performance guarantees for policy learning
• Concentration inequalities for two-sample rank processes with application to bipartite ranking
• A local Vapnik-Chervonenkis complexity
• Estimation bounds and sharp oracle inequalities of regularized procedures with Lipschitz loss functions
• Convergence rates of least squares regression estimators with heavy-tailed errors
• Inference on covariance operators via concentration inequalities: \(k\)-sample tests, classification, and clustering via Rademacher complexities
• Localized Gaussian width of \(M\)-convex hulls with applications to Lasso and convex aggregation
• Rademacher complexity for Markov chains: applications to kernel smoothing and Metropolis-Hastings
• Nonparametric estimation of low rank matrix valued function
• Nonasymptotic bounds for vector quantization in Hilbert spaces
• Minimax fast rates for discriminant analysis with errors in variables
• Statistical properties of kernel principal component analysis
• Model selection by bootstrap penalization for classification
• Fast learning rates in statistical inference through aggregation
• Statistical performance of support vector machines
• Ranking and empirical minimization of \(U\)-statistics
• Global uniform risk bounds for wavelet deconvolution estimators
• Rates of convergence in active learning
• Empirical risk minimization is optimal for the convex aggregation problem
• Minimax adaptive dimension reduction for regression
• Aggregation for Gaussian regression
• Simultaneous adaptation to the margin and to complexity in classification
• Empirical minimization
• Concentration inequalities and asymptotic results for ratio type empirical processes
• Bandwidth selection in kernel empirical risk minimization via the gradient
• Square root penalty: Adaption to the margin in classification and in edge estimation
• Complexities of convex combinations and bounding the generalization error in classification
• Local Rademacher complexities
• Classifiers of support vector machine type with \(\ell_1\) complexity regularization
• Complex sampling designs: uniform limit theorems and applications
• Compressive statistical learning with random feature moments
• Gibbs posterior concentration rates under sub-exponential type losses
• Nonasymptotic analysis of robust regression with modified Huber's loss
• Measuring the capacity of sets of functions in the analysis of ERM
• Tikhonov, Ivanov and Morozov regularization for support vector machine learning
• On the optimality of sample-based estimates of the expectation of the empirical minimizer
• scientific article; zbMATH DE number 1804106 (Why is no real title available?)
• Local learning estimates by integral operators
• Theory of Classification: a Survey of Some Recent Advances
• Noisy discriminant analysis with boundary assumptions
• Fast rates for empirical vector quantization
• FAST RATES FOR ESTIMATION ERROR AND ORACLE INEQUALITIES FOR MODEL SELECTION
• Inverse statistical learning
• Complexity versus agreement for many views. Co-regularization for multi-view semi-supervised learning
• The two-sample problem for Poisson processes: adaptive tests with a nonasymptotic wild bootstrap approach
• A statistical view of clustering performance through the theory of U-processes
• Random design analysis of ridge regression
• Risk bounds for CART classifiers under a margin condition
• Concentration inequalities and confidence bands for needlet density estimators on compact homogeneous manifolds
• General nonexact oracle inequalities for classes with a subexponential envelope
• scientific article; zbMATH DE number 1552503 (Why is no real title available?)
• Margin-adaptive model selection in statistical learning
• Rademacher penalties and structural risk minimization
• Local Rademacher complexity-based learning guarantees for multi-task learning
• Learning Theory
• 10.1162/153244303321897690
• Optimal exponential bounds on the accuracy of classification

This page was built for publication: Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2373576)