Rejoinder: Local Rademacher complexities and oracle inequalities in risk minimization

Rejoinder: 2004 IMS Medallion Lecture: Local Rademacher complexities and oracle inequalities in risk minimization [arXiv:0708.0083]

• Publication year

  2006

• Venue

  Annals of Statistics

• Publication date

  2006-12-01

• Fields of study

  Mathematics, Computer Science

• Identifiers
  DOI 10.1214/009053606000001082arXiv 0708.0135
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Statistical Learning Theory

  2021cited by this paper
• Statistical performance of support vector machines

  2008cited by this paper
• Aggregation for Gaussian regression

  2007cited by this paper
• Reconstruction and Subgaussian Operators in Asymptotic Geometric Analysis

  2007cited by this paper
• Concentration inequalities and asymptotic results for ratio type empirical processes

  2006cited by this paper
• Stable recovery of sparse overcomplete representations in the presence of noise

  2006cited by this paper
• Convexity, Classification, and Risk Bounds

  2006influential reference
• Empirical minimization

  2006cited by this paper
• For most large underdetermined systems of linear equations the minimal 𝓁1‐norm solution is also the sparsest solution

  2006cited by this paper
• For most large underdetermined systems of equations, the minimal 𝓁1‐norm near‐solution approximates the sparsest near‐solution

  2006cited by this paper
• Some applications of concentration inequalities to statistics

  2005influential reference
• Square root penalty: Adaptation to the margin in classification and in edge estimation

  2005influential reference
• Geometric approach to error-correcting codes and reconstruction of signals

  2005cited by this paper
• Local Rademacher complexities

  2005influential reference
• The Dantzig selector: Statistical estimation when P is much larger than n

  2005cited by this paper
• Moment inequalities for functions of independent random variables

  2005cited by this paper
• Aggregation for Regression Learning

  2004cited by this paper
• Bounding the generalization error of convex combinations of classifiers: balancing the dimensionality and the margins

  2004cited by this paper
• Model selection by bootstrap penalization for classification

  2004cited by this paper
• Complexity regularization via localized random penalties

  2004influential reference
• Complexities of convex combinations and bounding the generalization error in classification

  2004cited by this paper
• Rademacher Processes and Bounding the Risk of Function Learning

  2004influential reference
• Statistical behavior and consistency of classification methods based on convex risk minimization

  2003cited by this paper
• Ratio Limit Theorems for Empirical Processes

  2003cited by this paper
• On the Bayes-risk consistency of regularized boosting methods

  2003cited by this paper
• Optimal aggregation of classifiers in statistical learning

  2003influential reference
• On the Rate of Convergence of Regularized Boosting Classifiers

  2003influential reference
• Geometric Parameters of Kernel Machines

  2002cited by this paper
• Une inégalité de concentration à gauche pour les processus empiriques

  2002cited by this paper
• Empirical margin distributions and bounding the generalization error of combined classifiers

  2002cited by this paper
• Improving the sample complexity using global data

  2002influential reference
• A Bennett concentration inequality and its application to suprema of empirical processes

  2002cited by this paper
• Model selection for regression on a random design

  2002cited by this paper
• Some Local Measures of Complexity of Convex Hulls and Generalization Bounds

  2002cited by this paper
• A Distribution-Free Theory of Nonparametric Regression

  2002cited by this paper
• On consistency of kernel density estimators for randomly censored data: rates holding uniformly over adaptive intervals

  2001cited by this paper
• Rademacher penalties and structural risk minimization

  2001cited by this paper
• Empirical Processes in M-Estimation

  2001cited by this paper
• Uniform Central Limit Theorems

  2001cited by this paper
• An Empirical Process Approach to the Uniform Consistency of Kernel-Type Function Estimators

  2000cited by this paper
• Inequalities for uniform deviations of averages from expectations with applications to nonparametric regression

  2000cited by this paper
• A sharp concentration inequality with applications

  1999influential reference
• Smooth Discrimination Analysis

  1999influential reference
• Neural Network Learning: Theoretical Foundations

  1999influential reference
• Risk bounds for model selection via penalization

  1999cited by this paper
• Decoupling: From Dependence to Independence

  1998cited by this paper
• From Model Selection to Adaptive Estimation

  1997cited by this paper
• New concentration inequalities in product spaces

  1996influential reference
• A new look at independence

  1996influential reference
• A Probabilistic Theory of Pattern Recognition

  1996cited by this paper
• Weak Convergence and Empirical Processes: With Applications to Statistics

  1996influential reference
• Convergence Rate of Sieve Estimates

  1994cited by this paper
• Sharper Bounds for Gaussian and Empirical Processes

  1994cited by this paper
• Some Limit Theorems for Empirical Processes

  1984cited by this paper
• Monocular 3 D tracking of deformable surfaces using sequential second order cone programming

  1979cited by this paper
• Probability on Banach spaces

  1978cited by this paper
• A Class of Statistics with Asymptotically Normal Distribution

  1948cited by this paper
• Fast Rates of Uniform Convergence and Oracle Inequalities for Model Selection

  year unknowninfluential reference
• c ○ 2002 Kluwer Academic Publishers. Manufactured in The Netherlands. Model Selection and Error Estimation ∗

  year unknowncited by this paper
• Eecient Agnostic Learning of Neural Networks with Bounded Fan-in

  year unknowncited by this paper

• Fast Rates in Statistical and Online Learning

  2022influential citation
• Deep learning: a statistical viewpoint

  2021cites this paper
• Multiplier U-processes: Sharp bounds and applications

  2021cites this paper
• Online Active Learning with Surrogate Loss Functions

  2021cites this paper
• Optimal linear discriminators for the discrete choice model in growing dimensions

  2021influential citation
• of the Bernoulli Society for Mathematical Statistics and Probability Volume Twenty Eight Number One February 2022

  2021cites this paper
• Information geometry approach to parameter estimation in hidden Markov model

  2021cites this paper
• Linear expectile regression under massive data

  2021cites this paper
• Concentration bounds for the extremal variogram

  2021influential citation
• Discussion on Minimal Penalty and the Slope Heuristic: A Survey, by S. Arlot

  2021cites this paper
• On the statistical complexity of quantum circuits

  2021cites this paper
• Novel Concentration of Measure Bounds with Applications to Fairness in Machine Learning

  2020cites this paper
• Advantage of Deep Neural Networks for Estimating Functions with Singularity on Hypersurfaces

  2020influential citation
• Optimal oracle inequalities for solving projected fixed-point equations

  2020cites this paper
• Policy Transforms and Learning Optimal Policies

  2020influential citation
• Analyzing the discrepancy principle for kernelized spectral filter learning algorithms

  2020influential citation
• Maximum-and-Concatenation Networks

  2020cites this paper
• Contributions à l'apprentissage statistique : estimation de densité, agrégation d'experts et forêts aléatoires. (Contributions to statistical learning : density estimation, expert aggregation and random forests)

  2020influential citation
• Introduction

  2019cites this paper
• Localization and uniform laws

  2019cites this paper
• Random matrices and covariance estimation

  2019cites this paper
• Principal component analysis in high dimensions

  2019cites this paper
• Decomposability and restricted strong convexity

  2019cites this paper
• Nonparametric least squares

  2019cites this paper
• Matrix estimation with rank constraints

  2019cites this paper
• Graphical models for high-dimensional data

  2019cites this paper
• Minimax Lower Bounds

  2019cites this paper
• Foundations of deep convolutional models through kernel methods. (Méthodes à noyaux pour les réseaux convolutionnels profonds)

  2019cites this paper
• Towards More Scalable and Robust Machine Learning

  2019cites this paper
• Metric entropy and its uses

  2019cites this paper
• Sparse linear models in high dimensions

  2019cites this paper
• Fast classification rates without standard margin assumptions

  2019cites this paper
• Basic tail and concentration bounds

  2019cites this paper
• Fast-rate PAC-Bayes Generalization Bounds via Shifted Rademacher Processes

  2019cites this paper
• The “Five W” of MS and EE

  2019cites this paper
• Complexity-Based Methods

  2019cites this paper
• Fast generalization error bound of deep learning without scale invariance of activation functions

  2019cites this paper
• Robust high dimensional learning for Lipschitz and convex losses

  2019cites this paper
• Reproducing kernel Hilbert spaces

  2019cites this paper
• High-Dimensional Statistics

  2019cites this paper
• Uniform laws of large numbers

  2019cites this paper
• Robust statistical learning with Lipschitz and convex loss functions

  2019cites this paper
• Optimal survey schemes for stochastic gradient descent with applications to M-estimation

  2019cites this paper
• An Empirical Study on Regularization of Deep Neural Networks by Local Rademacher Complexity

  2019cites this paper
• Efficient methods for signal detection from correlated adverse events in clinical trials

  2019cites this paper
• Convergence rates for empirical barycenters in metric spaces: curvature, convexity and extendable geodesics

  2018cites this paper
• Joint regression analysis of mixed-type outcome data via efficient scores

  2018cites this paper
• Singularity, misspecification and the convergence rate of EM

  2018cites this paper
• Fast generalization error bound of deep learning from a kernel perspective

  2018cites this paper
• Model selection and error estimation without the agonizing pain

  2018cites this paper
• From Gauss to Kolmogorov: Localized Measures of Complexity for Ellipses

  2018cites this paper
• Deep Neural Networks for Estimation and Inference: Application to Causal Effects and Other Semiparametric Estimands

  2018cites this paper
• Multi-Class Learning: From Theory to Algorithm

  2018cites this paper
• Linear regression and learning : contributions to regularization and aggregation methods

  2018cites this paper
• Submitted to the Annals of Statistics CONVERGENCE RATES OF LEAST SQUARES REGRESSION ESTIMATORS WITH HEAVY-TAILED ERRORS By Qiyang

  2018cites this paper
• Minimax-inspired Semiparametric Estimation and Causal Inference

  2018cites this paper
• Concentration Inequalities for Samples without Replacement

  2017cites this paper
• Measuring the expressivity of graph kernels through Statistical Learning Theory

  2017cites this paper
• A concentration inequality based statistical methodology for inference on covariance matrices and operators

  2017cites this paper
• Sampling and empirical risk minimization

  2017cites this paper
• Learning Objectives for Treatment Effect Estimation

  2017cites this paper
• Learning-Based Method with Valence Shifters for Sentiment Analysis

  2017cites this paper
• Nonparametric Active Learning , Part 1 : Smooth Regression Functions

  2017cites this paper
• Infinite Kernel Learning: Generalization Bounds and Algorithms

  2017cites this paper
• Quantum computing and supervised machine learning

  2017cites this paper
• Localized Gaussian width of $M$-convex hulls with applications to Lasso and convex aggregation

  2017cites this paper
• Convergence rates of least squares regression estimators with heavy-tailed errors

  2017cites this paper
• Balancing Out Regression Error: Efficient Treatment Effect Estimation without Smooth Propensities

  2017cites this paper
• Statistical Consistency of Kernel PCA with Random Features

  2017cites this paper
• Robust multicategory support vector machines using difference convex algorithm

  2017cites this paper
• Generalization Analysis for Ranking Using Integral Operator

  2017influential citation
• Empirical variance minimization with applications in variance reduction and optimal control

  2017influential citation
• Nonparametric regression using deep neural networks with ReLU activation function

  2017influential citation
• Discussion of “concentration for (regularized) empirical risk minimization” by Sara van de Geer and Martin Wainwright

  2017cites this paper
• Неравенства концентрации для выборок без возвращений@@@On two approaches to concentration for sampling without replacement

  2016cites this paper
• Localization of VC Classes: Beyond Local Rademacher Complexities

  2016cites this paper
• Inference on Covariance Operators via Concentration Inequalities: k-sample Tests, Classification, and Clustering via Rademacher Complexities

  2016cites this paper
• Tikhonov, Ivanov and Morozov regularization for support vector machine learning

  2016cites this paper
• Kernel ridge vs. principal component regression: minimax bounds and adaptability of regularization operators

  2016cites this paper
• Fast Rates with Unbounded Losses

  2016influential citation
• Asymptotic behavior of \(\ell_p\)-based Laplacian regularization in semi-supervised learning

  2016cites this paper
• Distributed Machine Learning with Communication Constraints

  2016cites this paper
• A local Vapnik-Chervonenkis complexity

  2016cites this paper
• Fast Randomized Algorithms for Convex Optimization and Statistical Estimation

  2016cites this paper
• Structural exploration and inference of the network

  2016cites this paper
• Machine Learning at Extremes

  2016cites this paper
• HONEST CONFIDENCE SETS IN NONPARAMETRIC IV REGRESSION AND OTHER ILL-POSED MODELS

  2016cites this paper
• Sharp oracle inequalities in aggregation and shape restricted regression

  2016cites this paper
• THÈSE DE DOCTORAT ÈS MATHÉMATIQUES

  2016cites this paper
• Fast Rates for General Unbounded Loss Functions: From ERM to Generalized Bayes

  2016cites this paper
• Noisy discriminant analysis with boundary assumptions

  2015cites this paper
• Refined Error Bounds for Several Learning Algorithms

  2015influential citation
• On Singular Values of Random Matrices

  2015cites this paper
• Optimal model selection in heteroscedastic regression using piecewise polynomials

  2015cites this paper
• Local Rademacher Complexity: Sharper risk bounds with and without unlabeled samples

  2015cites this paper
• Estimation robuste de distributions à queue lourde Robust estimation of heavy-tailed distributions

  2015cites this paper
• Fast convergence of extended Rademacher Complexity bounds

  2015cites this paper
• Mathematical Foundations of Infinite-Dimensional Statistical Models

  2015cites this paper
• On Anomaly Ranking and Excess-Mass Curves

  2015cites this paper
• Hardware-Friendly Activity Recognition with Fixed-Point Arithmetic

  2015cites this paper