Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
From MaRDI portal
Publication:2373576
Nonparametric regression and quantile regression (62G08) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05) Pattern recognition, speech recognition (68T10) Computational learning theory (68Q32) Probability theory on algebraic and topological structures (60B99)
Abstract: Let be a class of measurable functions defined on a probability space . 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 , . Given a solution 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 . 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
Cites work
- 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?)
- 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
- 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 new method for estimation and model selection: \(\rho\)-estimation
- Empirical risk minimization for heavy-tailed losses
- Oracle inequalities in empirical risk minimization and sparse recovery problems. École d'Été de Probabilités de Saint-Flour XXXVIII-2008.
- Statistical performance of support vector machines
- Ranking and empirical minimization of \(U\)-statistics
- Singularity, misspecification and the convergence rate of EM
- 10.1162/153244303321897690
- Global uniform risk bounds for wavelet deconvolution estimators
- Nonasymptotic bounds for vector quantization in Hilbert spaces
- Convergence rates of least squares regression estimators with heavy-tailed errors
- Local Rademacher complexities
- General nonexact oracle inequalities for classes with a subexponential envelope
- Square root penalty: Adaption to the margin in classification and in edge estimation
- Sparse recovery in convex hulls via entropy penalization
- Risk bounds for CART classifiers under a margin condition
- Statistical properties of kernel principal component analysis
- Aggregation for Gaussian regression
- On the optimality of the aggregate with exponential weights for low temperatures
- Obtaining fast error rates in nonconvex situations
- Tikhonov, Ivanov and Morozov regularization for support vector machine learning
- Complexities of convex combinations and bounding the generalization error in classification
- Approximation properties of certain operator-induced norms on Hilbert spaces
- Fast learning rates in statistical inference through aggregation
- Margin-adaptive model selection in statistical learning
- Direct importance estimation for covariate shift adaptation
- Random design analysis of ridge regression
- Sampling and empirical risk minimization
- Variance-based regularization with convex objectives
- Compressive statistical learning with random feature moments
- A high-dimensional Wilks phenomenon
- Classifiers of support vector machine type with \(\ell_1\) complexity regularization
- Honest confidence sets in nonparametric IV regression and other ill-posed models
- Fast rates for empirical vector quantization
- The two-sample problem for Poisson processes: adaptive tests with a nonasymptotic wild bootstrap approach
- Bayesian fractional posteriors
- Fast learning rates for plug-in classifiers
- Optimal survey schemes for stochastic gradient descent with applications to \(M\)-estimation
- Inverse statistical learning
- Empirical risk minimization is optimal for the convex aggregation problem
- A statistical view of clustering performance through the theory of \(U\)-processes
- A local Vapnik-Chervonenkis complexity
- U-Processes and Preference Learning
- Rates of convergence in active learning
- A universal procedure for aggregating estimators
- FAST RATES FOR ESTIMATION ERROR AND ORACLE INEQUALITIES FOR MODEL SELECTION
- Concentration inequalities and confidence bands for needlet density estimators on compact homogeneous manifolds
- On concentration for (regularized) empirical risk minimization
- Simultaneous adaptation to the margin and to complexity in classification
- Adaptive kernel methods using the balancing principle
- Local learning estimates by integral operators
- Rho-estimators revisited: general theory and applications
- Minimax fast rates for discriminant analysis with errors in variables
- Local Rademacher complexity: sharper risk bounds with and without unlabeled samples
- Empirical minimization
- Tests and estimation strategies associated to some loss functions
- Oracle inequalities for cross-validation type procedures
- Rademacher complexity for Markov chains: applications to kernel smoothing and Metropolis-Hastings
- An elementary analysis of ridge regression with random design
- Sparsity in penalized empirical risk minimization
- Adaptive estimation of a distribution function and its density in sup-norm loss by wavelet and spline projections
- Nonparametric estimation of low rank matrix valued function
- Fast learning rate of non-sparse multiple kernel learning and optimal regularization strategies
- Concentration inequalities and asymptotic results for ratio type empirical processes
- General oracle inequalities for model selection
- Learning Theory
- Optimal exponential bounds on the accuracy of classification
- Regularization in kernel learning
- Sharper lower bounds on the performance of the empirical risk minimization algorithm
- scientific article; zbMATH DE number 1552503 (Why is no real title available?)
- Model selection by bootstrap penalization for classification
- Theory of Classification: a Survey of Some Recent Advances
- Complexity regularization via localized random penalties
- A no-free-lunch theorem for multitask learning
- Model selection by resampling penalization
- Parametric or nonparametric? A parametricness index for model selection
- Rademacher penalties and structural risk minimization
- Robust supervised learning with coordinate gradient descent
- Sample average approximation for stochastic programming with equality constraints
- Concentration inequalities for two-sample rank processes with application to bipartite ranking
- Concentration inequalities for samples without replacement
- Optimal robust mean and location estimation via convex programs with respect to any pseudo-norms
- scientific article; zbMATH DE number 1804106 (Why is no real title available?)
- Measuring distributional asymmetry with Wasserstein distance and Rademacher symmetrization
- Joint regression analysis of mixed-type outcome data via efficient scores
- Solving PDEs on spheres with physics-informed convolutional neural networks
- On the optimality of the empirical risk minimization procedure for the convex aggregation problem
- On least squares estimation under heteroscedastic and heavy-tailed errors
- Minimax adaptive dimension reduction for regression
- Bandwidth selection in kernel empirical risk minimization via the gradient
- Complexity versus agreement for many views. Co-regularization for multi-view semi-supervised learning
- Robust statistical learning with Lipschitz and convex loss functions
- On the optimality of sample-based estimates of the expectation of the empirical minimizer
- A moment-matching approach to testable learning and a new characterization of Rademacher complexity
- 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
- Discussion of ``On concentration for (regularized) empirical risk minimization by Sara van de Geer and Martin Wainwright
- Measuring the capacity of sets of functions in the analysis of ERM
- Fast generalization error bound of deep learning without scale invariance of activation functions
- Set structured global empirical risk minimizers are rate optimal in general dimensions
- From Gauss to Kolmogorov: localized measures of complexity for ellipses
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)
