Optimal aggregation of classifiers in statistical learning.

DOI10.1214/aos/1079120131zbMath1105.62353OpenAlexW2043919728WikidataQ101069147 ScholiaQ101069147MaRDI QIDQ1884608

Publication date: 5 November 2004

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

Full work available at URL: https://projecteuclid.org/euclid.aos/1079120131

zbMATH Keywords

classification margins empirical processes statistical learning optimal rates aggregation of classifiers complexity of classes of sets

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05) Nonparametric inference (62G99)

Related Items

Embedding Learning, The Nonstochastic Multiarmed Bandit Problem, Crowdsourcing label quality: a theoretical analysis, Classification with reject option, Noisy discriminant analysis with boundary assumptions, A linear response bandit problem, Smooth Contextual Bandits: Bridging the Parametric and Nondifferentiable Regret Regimes, Toward Efficient Ensemble Learning with Structure Constraints: Convergent Algorithms and Applications, Classifiers of support vector machine type with \(\ell_1\) complexity regularization, Minimum clinically important difference in medical studies, On boundary estimation, Unnamed Item, Transfer learning for nonparametric classification: minimax rate and adaptive classifier, Complex sampling designs: uniform limit theorems and applications, Error Analysis of Coefficient-Based Regularized Algorithm for Density-Level Detection, Intrinsic Dimension Adaptive Partitioning for Kernel Methods, Benefit of Interpolation in Nearest Neighbor Algorithms, Learning from Non-iid Data: Fast Rates for the One-vs-All Multiclass Plug-in Classifiers, Simplex-based Multinomial Logistic Regression with Diverging Numbers of Categories and Covariates, Fast convergence rates of deep neural networks for classification, Classification with minimum ambiguity under distribution heterogeneity, Debiased machine learning of set-identified linear models, Error analysis of classification learning algorithms based on LUMs loss, Unnamed Item, Unnamed Item, Unnamed Item, Optimal discriminant analysis in high-dimensional latent factor models, Deep neural network classifier for multidimensional functional data, Statistically Efficient Advantage Learning for Offline Reinforcement Learning in Infinite Horizons, Collaborative Multilabel Classification, Optimal convergence rates of deep neural networks in a classification setting, Transfer learning for contextual multi-armed bandits, Improving reinforcement learning algorithms: Towards optimal learning rate policies, Multiclass classification for multidimensional functional data through deep neural networks, Gibbs posterior concentration rates under sub-exponential type losses, A Sparse Random Projection-Based Test for Overall Qualitative Treatment Effects, Online Decision Making with High-Dimensional Covariates, A Note on Support Vector Machines with Polynomial Kernels, Learning Theory Estimates with Observations from General Stationary Stochastic Processes, Generalization Analysis of Fredholm Kernel Regularized Classifiers, Learning Rates for Classification with Gaussian Kernels, Large-Scale Machine Learning with Stochastic Gradient Descent, Optimization Methods for Large-Scale Machine Learning, Unnamed Item, Unnamed Item, Fast rate of convergence in high-dimensional linear discriminant analysis, SVM Soft Margin Classifiers: Linear Programming versus Quadratic Programming, Approximation with polynomial kernels and SVM classifiers, Unnamed Item, Variance-based regularization with convex objectives, Some properties of Gaussian reproducing kernel Hilbert spaces and their implications for function approximation and learning theory, Adaptation to lowest density regions with application to support recovery, Randomized allocation with arm elimination in a bandit problem with covariates, Bandwidth selection in kernel empirical risk minimization via the gradient, Measuring the Capacity of Sets of Functions in the Analysis of ERM, Theory of Classification: a Survey of Some Recent Advances, On Reject and Refine Options in Multicategory Classification, On the Optimality of Sample-Based Estimates of the Expectation of the Empirical Minimizer, Consistency of plug-in confidence sets for classification in semi-supervised learning, ANALYSIS OF CLASSIFICATION WITH A REJECT OPTION, Unnamed Item, Unnamed Item, Adaptive Estimation of the Optimal ROC Curve and a Bipartite Ranking Algorithm, Robust randomized optimization with k nearest neighbors, Confidence sets with expected sizes for Multiclass Classification, Online regularized generalized gradient classification algorithms, Unnamed Item, Unnamed Item, Square root penalty: Adaption to the margin in classification and in edge estimation, Nonparametric Pricing Analytics with Customer Covariates, Unnamed Item, Unnamed Item, Unnamed Item, Comparison theorems on large-margin learning, Estimating Individualized Treatment Rules Using Outcome Weighted Learning, A new learning paradigm: learning using privileged information, Complexity regularization via localized random penalties, Statistical inference for the mean outcome under a possibly non-unique optimal treatment strategy, Statistical consistency of coefficient-based conditional quantile regression, Classification in general finite dimensional spaces with the \(k\)-nearest neighbor rule, Woodroofe's one-armed bandit problem revisited, Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder), Convergence rates of deep ReLU networks for multiclass classification, PRIM analysis, Model selection by bootstrap penalization for classification, Reweighting samples under covariate shift using a Wasserstein distance criterion, Fast learning rates in statistical inference through aggregation, Asymptotic normality of plug-in level set estimates, The multi-armed bandit problem with covariates, Risk bounds for statistical learning, On regularization algorithms in learning theory, Multi-kernel regularized classifiers, Inverse statistical learning, Best subset binary prediction, Robust statistical learning with Lipschitz and convex loss functions, Ranking data with ordinal labels: optimality and pairwise aggregation, Approximation on variable exponent spaces by linear integral operators, Optimal rates for plug-in estimators of density level sets, Generalized density clustering, Overlaying classifiers: A practical approach to optimal scoring, Regularization in statistics, A statistical view of clustering performance through the theory of \(U\)-processes, \(\ell_{1}\)-penalization for mixture regression models, Quantitative convergence analysis of kernel based large-margin unified machines, Adaptive partitioning schemes for bipartite ranking, Learning noisy linear classifiers via adaptive and selective sampling, Statistical performance of support vector machines, High-dimensional generalized linear models and the lasso, Ranking and empirical minimization of \(U\)-statistics, On the optimality of the empirical risk minimization procedure for the convex aggregation problem, The regularized least squares algorithm and the problem of learning halfspaces, Rates of convergence in active learning, Recursive aggregation of estimators by the mirror descent algorithm with averaging, Deviation inequalities for random polytopes in arbitrary convex bodies, Estimating conditional quantiles with the help of the pinball loss, Empirical risk minimization is optimal for the convex aggregation problem, Risk bounds for CART classifiers under a margin condition, Optimal upper and lower bounds for the true and empirical excess risks in heteroscedastic least-squares regression, Oracle inequalities for cross-validation type procedures, Upper bounds and aggregation in bipartite ranking, Classification with minimax fast rates for classes of Bayes rules with sparse representation, General oracle inequalities for model selection, The false discovery rate for statistical pattern recognition, Penalized empirical risk minimization over Besov spaces, On the optimality of the aggregate with exponential weights for low temperatures, Mirror averaging with sparsity priors, ERM and RERM are optimal estimators for regression problems when malicious outliers corrupt the labels, Margin-adaptive model selection in statistical learning, Adaptive kernel methods using the balancing principle, Fast learning from \(\alpha\)-mixing observations, Optimal learning with \textit{Q}-aggregation, Support vector machines with a reject option, Analysis of approximation by linear operators on variable \(L_\rho^{p(\cdot)}\) spaces and applications in learning theory, Obtaining fast error rates in nonconvex situations, Methods for estimation of convex sets, Performance guarantees for policy learning, Simultaneous adaptation to the margin and to complexity in classification, Feature elimination in kernel machines in moderately high dimensions, Classification algorithms using adaptive partitioning, Optimal exponential bounds on the accuracy of classification, Optimal rates for nonparametric F-score binary classification via post-processing, A strong converse bound for multiple hypothesis testing, with applications to high-dimensional estimation, Optimal rates of aggregation in classification under low noise assumption, Counting and enumerating aggregate classifiers, Logistic classification with varying gaussians, Learning rates for multi-kernel linear programming classifiers, Estimation of regression contour clusters -- an application of the excess mass approach to regression, Surrogate losses in passive and active learning, Classification with Gaussians and convex loss. II: Improving error bounds by noise conditions, Performance guarantees for individualized treatment rules, Learning errors of linear programming support vector regression, Concentration inequalities and asymptotic results for ratio type empirical processes, A high-dimensional Wilks phenomenon, Fast rates for support vector machines using Gaussian kernels, Fast learning rates for plug-in classifiers, Unregularized online algorithms with varying Gaussians, Iterative feature selection in least square regression estimation, PAC-Bayesian bounds for randomized empirical risk minimizers, Robustness of learning algorithms using hinge loss with outlier indicators, Conditional probability estimation based classification with class label missing at random, A MOM-based ensemble method for robustness, subsampling and hyperparameter tuning, Optimal weighted nearest neighbour classifiers, Set structured global empirical risk minimizers are rate optimal in general dimensions, Estimation bounds and sharp oracle inequalities of regularized procedures with Lipschitz loss functions, Asymptotic normality of support vector machine variants and other regularized kernel methods, Multiplier \(U\)-processes: sharp bounds and applications, Adaptive learning rates for support vector machines working on data with low intrinsic dimension, Optimal linear discriminators for the discrete choice model in growing dimensions, Adaptive transfer learning, Two-level monotonic multistage recommender systems, Robust empirical Bayes tests for continuous distributions, Generalization error bounds of dynamic treatment regimes in penalized regression-based learning, Tnn: a transfer learning classifier based on weighted nearest neighbors, Minimax fast rates for discriminant analysis with errors in variables, A no-free-lunch theorem for multitask learning

Cites Work