Fast learning rates for plug-in classifiers

DOI10.1214/009053606000001217zbMath1118.62041arXiv0708.2321OpenAlexW1996437515MaRDI QIDQ995418

Jean-Yves Audibert, Alexandre B. Tsybakov

Publication date: 3 September 2007

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

Full work available at URL: https://arxiv.org/abs/0708.2321

zbMATH Keywords

classification statistical learning minimax lower bounds fast rates of convergence excess risk plug-in classifiers

Mathematics Subject Classification ID

Nonparametric regression and quantile regression (62G08) Density estimation (62G07) Classification and discrimination; cluster analysis (statistical aspects) (62H30) Characterization and structure theory for multivariate probability distributions; copulas (62H05) Pattern recognition, speech recognition (68T10)

Related Items

Sensitivity Analysis via the Proportion of Unmeasured Confounding, Statistical inference for the mean outcome under a possibly non-unique optimal treatment strategy, Optimal classification and nonparametric regression for functional data, Classification in general finite dimensional spaces with the \(k\)-nearest neighbor rule, Convergence rates of deep ReLU networks for multiclass classification, Noisy discriminant analysis with boundary assumptions, Bandit and covariate processes, with finite or non-denumerable set of arms, Smoothness-Adaptive Contextual Bandits, Smooth Contextual Bandits: Bridging the Parametric and Nondifferentiable Regret Regimes, PAC-Bayesian high dimensional bipartite ranking, Supervised Classification for a Family of Gaussian Functional Models, Fast learning rates in statistical inference through aggregation, The multi-armed bandit problem with covariates, Unnamed Item, Transfer learning for nonparametric classification: minimax rate and adaptive classifier, Inverse statistical learning, Local Rademacher complexity: sharper risk bounds with and without unlabeled samples, Ranking data with ordinal labels: optimality and pairwise aggregation, Optimal functional supervised classification with separation condition, Optimal rates for plug-in estimators of density level sets, Generalized density clustering, Intrinsic Dimension Adaptive Partitioning for Kernel Methods, Benefit of Interpolation in Nearest Neighbor Algorithms, Posterior concentration and fast convergence rates for generalized Bayesian learning, Overlaying classifiers: A practical approach to optimal scoring, Confidence regions for level sets, Learning from Non-iid Data: Fast Rates for the One-vs-All Multiclass Plug-in Classifiers, Asymptotic Theory of \(\boldsymbol \ell _1\) -Regularized PDE Identification from a Single Noisy Trajectory, Classification Trees for Imbalanced Data: Surface-to-Volume Regularization, Fast convergence rates of deep neural networks for classification, Classification with minimum ambiguity under distribution heterogeneity, Unnamed Item, An adaptive multiclass nearest neighbor classifier, Deep neural network classifier for multidimensional functional data, Self-supervised Metric Learning in Multi-View Data: A Downstream Task Perspective, Local nearest neighbour classification with applications to semi-supervised learning, Adaptive novelty detection with false discovery rate guarantee, Statistically Efficient Advantage Learning for Offline Reinforcement Learning in Infinite Horizons, Distributed adaptive nearest neighbor classifier: algorithm and theory, Optimal subgroup selection, Optimal convergence rates of deep neural networks in a classification setting, Transfer learning for contextual multi-armed bandits, Classification via local multi-resolution projections, Upper bounds and aggregation in bipartite ranking, A Sparse Random Projection-Based Test for Overall Qualitative Treatment Effects, Selection of variables and dimension reduction in high-dimensional non-parametric regression, Penalized empirical risk minimization over Besov spaces, Noisy independent factor analysis model for density estimation and classification, Margin-adaptive model selection in statistical learning, Sharp instruments for classifying compliers and generalizing causal effects, Multi-Armed Angle-Based Direct Learning for Estimating Optimal Individualized Treatment Rules With Various Outcomes, Quantum learning: asymptotically optimal classification of qubit states, Performance guarantees for policy learning, Simultaneous adaptation to the margin and to complexity in classification, Classification algorithms using adaptive partitioning, Pricing Bermudan options by nonparametric regression: optimal rates of convergence for lower estimates, Optimal exponential bounds on the accuracy of classification, Approximation of Limit State Surfaces in Monotonic Monte Carlo Settings, with Applications to Classification, Minimax semi-supervised set-valued approach to multi-class classification, Optimal rates for nonparametric F-score binary classification via post-processing, Improved classification rates under refined margin conditions, Optimal rates of aggregation in classification under low noise assumption, Choice of neighbor order in nearest-neighbor classification, Fast rate of convergence in high-dimensional linear discriminant analysis, Distribution-Free Prediction Sets, Surrogate losses in passive and active learning, Classification in postural style, Unnamed Item, Unnamed Item, Fast learning rates for plug-in classifiers, Randomized allocation with arm elimination in a bandit problem with covariates, Strongly universally consistent nonparametric regression and classification with privatised data, Optimal weighted nearest neighbour classifiers, Consistency of plug-in confidence sets for classification in semi-supervised learning, Convergence rates of generalization errors for margin-based classification, Least Ambiguous Set-Valued Classifiers With Bounded Error Levels, Estimation bounds and sharp oracle inequalities of regularized procedures with Lipschitz loss functions, Adaptive learning rates for support vector machines working on data with low intrinsic dimension, Marginal singularity and the benefits of labels in covariate-shift, Adaptive transfer learning, Regret lower bound and optimal algorithm for high-dimensional contextual linear bandit, Robust empirical Bayes tests for continuous distributions, Localized Gaussian width of \(M\)-convex hulls with applications to Lasso and convex aggregation, Statistical Inference for Online Decision Making via Stochastic Gradient Descent, Unnamed Item, Semiparametric single-index models for optimal treatment regimens with censored outcomes, Stochastic continuum-armed bandits with additive models: minimax regrets and adaptive algorithm, Towards convergence rate analysis of random forests for classification, Optimal Individualized Decision Rules Using Instrumental Variable Methods, Rejoinder: Optimal Individualized Decision Rules Using Instrumental Variable Methods, Unnamed Item, Unnamed Item, Tnn: a transfer learning classifier based on weighted nearest neighbors, Minimax fast rates for discriminant analysis with errors in variables

Cites Work