Local Rademacher complexities

DOI10.1214/009053605000000282zbMath1083.62034arXivmath/0508275OpenAlexW3100743579WikidataQ105584239 ScholiaQ105584239MaRDI QIDQ2583411

Olivier Bousquet, Shahar Mendelson, Bartlett, Peter L.

Publication date: 16 January 2006

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

Full work available at URL: https://arxiv.org/abs/math/0508275

zbMATH Keywords

error bounds concentration inequalities Rademacher averages data-dependent complexity

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Computational learning theory (68Q32) Analysis of algorithms and problem complexity (68Q25) Complexity and performance of numerical algorithms (65Y20)

Related Items

Learning models with uniform performance via distributionally robust optimization, Generalization bounds for non-stationary mixing processes, Online regularized learning with pairwise loss functions, Fast rates by transferring from auxiliary hypotheses, On the optimal estimation of probability measures in weak and strong topologies, Consistency analysis of an empirical minimum error entropy algorithm, Tikhonov, Ivanov and Morozov regularization for support vector machine learning, A reproducing kernel Hilbert space approach to high dimensional partially varying coefficient model, Influence diagnostics in support vector machines, Sparsity in penalized empirical risk minimization, Empirical variance minimization with applications in variance reduction and optimal control, On nonparametric classification with missing covariates, Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder), Smooth sparse coding via marginal regression for learning sparse representations, Regularization in kernel learning, Complexity of pattern classes and the Lipschitz property, Statistical properties of kernel principal component analysis, Model selection by bootstrap penalization for classification, Optimal dyadic decision trees, Learning without concentration for general loss functions, Fast learning rate of non-sparse multiple kernel learning and optimal regularization strategies, Localization of VC classes: beyond local Rademacher complexities, Fast rates of minimum error entropy with heavy-tailed noise, Estimation of partially conditional average treatment effect by double kernel-covariate balancing, Multi-kernel regularized classifiers, Inverse statistical learning, Local Rademacher complexity: sharper risk bounds with and without unlabeled samples, Robust statistical learning with Lipschitz and convex loss functions, Compressive statistical learning with random feature moments, A unified penalized method for sparse additive quantile models: an RKHS approach, Convergence rates for empirical barycenters in metric spaces: curvature, convexity and extendable geodesics, Handling concept drift via model reuse, Convergence of online pairwise regression learning with quadratic loss, Model selection in reinforcement learning, Statistical performance of support vector machines, Nonasymptotic upper bounds for the reconstruction error of PCA, On mean estimation for heteroscedastic random variables, Robustness and generalization, From Gauss to Kolmogorov: localized measures of complexity for ellipses, Nonparametric distributed learning under general designs, Bootstrap model selection for possibly dependent and heterogeneous data, Concentration estimates for learning with unbounded sampling, Newton Sketch: A Near Linear-Time Optimization Algorithm with Linear-Quadratic Convergence, Nonasymptotic analysis of robust regression with modified Huber's loss, Estimating conditional quantiles with the help of the pinball loss, On the empirical estimation of integral probability metrics, Optimal model selection in heteroscedastic regression using piecewise polynomial functions, Model selection by resampling penalization, Penalized empirical risk minimization over Besov spaces, ERM and RERM are optimal estimators for regression problems when malicious outliers corrupt the labels, Margin-adaptive model selection in statistical learning, Fast learning from \(\alpha\)-mixing observations, Transfer bounds for linear feature learning, An improved analysis of the Rademacher data-dependent bound using its self bounding property, Using the doubling dimension to analyze the generalization of learning algorithms, On the uniform convergence of empirical norms and inner products, with application to causal inference, Calibration of \(\epsilon\)-insensitive loss in support vector machines regression, Obtaining fast error rates in nonconvex situations, Bayesian fractional posteriors, The geometry of hypothesis testing over convex cones: generalized likelihood ratio tests and minimax radii, Fast generalization rates for distance metric learning. Improved theoretical analysis for smooth strongly convex distance metric learning, Optimal prediction for high-dimensional functional quantile regression in reproducing kernel Hilbert spaces, A tight upper bound on the generalization error of feedforward neural networks, Robust multicategory support vector machines using difference convex algorithm, Optimal convergence rate of the universal estimation error, Oracle inequalities for sparse additive quantile regression in reproducing kernel Hilbert space, Singularity, misspecification and the convergence rate of EM, Optimal learning rates of \(l^p\)-type multiple kernel learning under general conditions, Surrogate losses in passive and active learning, Approximation by neural networks and learning theory, Monte Carlo algorithms for optimal stopping and statistical learning, Empirical minimization, Rademacher Chaos Complexities for Learning the Kernel Problem, A local Vapnik-Chervonenkis complexity, Fast rates for support vector machines using Gaussian kernels, Learning without Concentration, VC Dimension, Fat-Shattering Dimension, Rademacher Averages, and Their Applications, Direct importance estimation for covariate shift adaptation, Online pairwise learning algorithms with convex loss functions, Theory of Classification: a Survey of Some Recent Advances, On the Optimality of Sample-Based Estimates of the Expectation of the Empirical Minimizer, Fast generalization error bound of deep learning without scale invariance of activation functions, When are epsilon-nets small?, Convergence rates of generalization errors for margin-based classification, Estimation bounds and sharp oracle inequalities of regularized procedures with Lipschitz loss functions, Convergence rates of least squares regression estimators with heavy-tailed errors, Approximation properties of certain operator-induced norms on Hilbert spaces, Rademacher complexity in Neyman-Pearson classification, Permutational Rademacher Complexity, 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, An elementary analysis of ridge regression with random design, Mean estimation and regression under heavy-tailed distributions: A survey, Improvement of multiple kernel learning using adaptively weighted regularization, Convolutional spectral kernel learning with generalization guarantees, Complexities of convex combinations and bounding the generalization error in classification, Boosting with early stopping: convergence and consistency, Minimax fast rates for discriminant analysis with errors in variables, Suboptimality of constrained least squares and improvements via non-linear predictors, Distribution-free robust linear regression, Low-Rank Covariance Function Estimation for Multidimensional Functional Data, Analysis of the Generalization Error: Empirical Risk Minimization over Deep Artificial Neural Networks Overcomes the Curse of Dimensionality in the Numerical Approximation of Black--Scholes Partial Differential Equations, Deep learning: a statistical viewpoint, A Statistical Learning Approach to Modal Regression, Noisy discriminant analysis with boundary assumptions, Online Linear Programming: Dual Convergence, New Algorithms, and Regret Bounds, Smooth Contextual Bandits: Bridging the Parametric and Nondifferentiable Regret Regimes, Graphical Convergence of Subgradients in Nonconvex Optimization and Learning, Unnamed Item, Unnamed Item, Full error analysis for the training of deep neural networks, Sample average approximation with heavier tails. I: Non-asymptotic bounds with weak assumptions and stochastic constraints, Sample average approximation with heavier tails II: localization in stochastic convex optimization and persistence results for the Lasso, Distributed learning for sketched kernel regression, Multi-kernel learning for multi-label classification with local Rademacher complexity, Regularized learning schemes in feature Banach spaces, PAC-learning with approximate predictors, Overall error analysis for the training of deep neural networks via stochastic gradient descent with random initialisation, Minimax rates for conditional density estimation via empirical entropy, Unnamed Item, Unnamed Item, Orthogonal statistical learning, Robust supervised learning with coordinate gradient descent, Data-adaptive discriminative feature localization with statistically guaranteed interpretation, Benign Overfitting and Noisy Features, Asset pricing with neural networks: significance tests, Metamodel construction for sensitivity analysis, Concentration Inequalities for Samples without Replacement, Learning with Convex Loss and Indefinite Kernels, Refined Generalization Bounds of Gradient Learning over Reproducing Kernel Hilbert Spaces, Kernelized Elastic Net Regularization: Generalization Bounds, and Sparse Recovery, U-Processes and Preference Learning, Unnamed Item, Unnamed Item, Unnamed Item, Unnamed Item, Variance-based regularization with convex objectives, Comments on: Support vector machines maximizing geometric margins for multi-class classification, Statistics of Robust Optimization: A Generalized Empirical Likelihood Approach, Comment, FAST RATES FOR ESTIMATION ERROR AND ORACLE INEQUALITIES FOR MODEL SELECTION, Unnamed Item, Unnamed Item, Learning rates for partially linear support vector machine in high dimensions, Unnamed Item, Estimating Individualized Treatment Rules Using Outcome Weighted Learning

Cites Work