Ranking and empirical minimization of \(U\)-statistics

DOI10.1214/009052607000000910zbMath1181.68160arXivmath/0603123OpenAlexW2950740915MaRDI QIDQ2426626

Stéphan Clémençon, Gábor Lugosi, Nicolas Vayatis

Publication date: 23 April 2008

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

Full work available at URL: https://arxiv.org/abs/math/0603123

zbMATH Keywords

moment inequalities \(U\)-processes statistical learning fast rates convex risk minimization VC classes theory of classification

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Computational learning theory (68Q32) Inequalities; stochastic orderings (60E15) Combinatorial probability (60C05) Prediction theory (aspects of stochastic processes) (60G25)

Related Items (82)

Online regularized learning with pairwise loss functions ⋮ A review on instance ranking problems in statistical learning ⋮ One-pass AUC optimization ⋮ Learning from binary labels with instance-dependent noise ⋮ Empirical variance minimization with applications in variance reduction and optimal control ⋮ Applications of concentration inequalities for statistical scoring and ranking problems ⋮ High-Dimensional Learning Under Approximate Sparsity with Applications to Nonsmooth Estimation and Regularized Neural Networks ⋮ PAC-Bayesian high dimensional bipartite ranking ⋮ Distributed spectral pairwise ranking algorithms ⋮ On the robustness of regularized pairwise learning methods based on kernels ⋮ Solving optimal stopping problems under model uncertainty via empirical dual optimisation ⋮ Robust estimation of \(U\)-statistics ⋮ ℓ¹-Norm support vector machine for ranking with exponentially strongly mixing sequence ⋮ Concordance and value information criteria for optimal treatment decision ⋮ GENERAL INEQUALITIES FOR GIBBS POSTERIOR WITH NONADDITIVE EMPIRICAL RISK ⋮ Ranking data with ordinal labels: optimality and pairwise aggregation ⋮ Overlaying classifiers: A practical approach to optimal scoring ⋮ A statistical view of clustering performance through the theory of \(U\)-processes ⋮ Scalable Collaborative Ranking for Personalized Prediction ⋮ A reduced-rank approach to predicting multiple binary responses through machine learning ⋮ Stochastic AUC optimization with general loss ⋮ Positive-unlabeled classification under class-prior shift: a prior-invariant approach based on density ratio estimation ⋮ Error analysis of kernel regularized pairwise learning with a strongly convex loss ⋮ Unnamed Item ⋮ Adaptive partitioning schemes for bipartite ranking ⋮ Learning rates for regularized least squares ranking algorithm ⋮ Random geometric graph: some recent developments and perspectives ⋮ Analysis of convergence performance of neural networks ranking algorithm ⋮ The fraud loss for selecting the model complexity in fraud detection ⋮ Regularized sample average approximation for high-dimensional stochastic optimization under low-rankness ⋮ On the variable bandwidth kernel estimation of conditional \(U\)-statistics at optimal rates in sup-norm ⋮ Quantitative robustness of instance ranking problems ⋮ Uniform consistency and uniform in bandwidth consistency for nonparametric regression estimates and conditional U-statistics involving functional data ⋮ Upper bounds and aggregation in bipartite ranking ⋮ The false discovery rate for statistical pattern recognition ⋮ The asymptotics of ranking algorithms ⋮ Variance reduction in Monte Carlo estimators via empirical variance minimization ⋮ Rank correlation estimators and their limiting distributions ⋮ Bias corrected regularization kernel method in ranking ⋮ Learning to rank on graphs ⋮ Guaranteed Classification via Regularized Similarity Learning ⋮ An empirical comparison of learning algorithms for nonparametric scoring: the \textsc{TreeRank} algorithm and other methods ⋮ Refined Generalization Bounds of Gradient Learning over Reproducing Kernel Hilbert Spaces ⋮ Online Pairwise Learning Algorithms ⋮ Stability and optimization error of stochastic gradient descent for pairwise learning ⋮ Query-dependent ranking and its asymptotic properties ⋮ Convergence analysis of an empirical eigenfunction-based ranking algorithm with truncated sparsity ⋮ U-Processes and Preference Learning ⋮ Co-clustering separately exchangeable network data ⋮ Learning rate of support vector machine for ranking ⋮ A Tuning-free Robust and Efficient Approach to High-dimensional Regression ⋮ Generalization performance of bipartite ranking algorithms with convex losses ⋮ Concentration inequalities for two-sample rank processes with application to bipartite ranking ⋮ Fast generalization rates for distance metric learning. Improved theoretical analysis for smooth strongly convex distance metric learning ⋮ The risk of trivial solutions in bipartite top ranking ⋮ Unregularized online learning algorithms with general loss functions ⋮ Unnamed Item ⋮ Generalization ability of online pairwise support vector machine ⋮ Sequential event prediction ⋮ The convergence rate of a regularized ranking algorithm ⋮ Approximation analysis of gradient descent algorithm for bipartite ranking ⋮ On empirical eigenfunction-based ranking with \(\ell^1\) norm regularization ⋮ Learning rates of multi-kernel regularized regression ⋮ Pairwise learning problems with regularization networks and Nyström subsampling approach ⋮ Weak convergence of the conditional U-statistics for locally stationary functional time series ⋮ Rademacher Chaos Complexities for Learning the Kernel Problem ⋮ Approximating high-dimensional infinite-order \(U\)-statistics: statistical and computational guarantees ⋮ A note on the use of empirical AUC for evaluating probabilistic forecasts ⋮ Online pairwise learning algorithms with convex loss functions ⋮ Lasso with convex loss: Model selection consistency and estimation ⋮ Online regularized pairwise learning with least squares loss ⋮ Convergence analysis of distributed multi-penalty regularized pairwise learning ⋮ Product-form estimators: exploiting independence to scale up Monte Carlo ⋮ Adaptive Estimation of the Optimal ROC Curve and a Bipartite Ranking Algorithm ⋮ Regularized ranking with convex losses and \(\ell^1\)-penalty ⋮ Multiplier \(U\)-processes: sharp bounds and applications ⋮ Asymptotic linear expansion of regularized M-estimators ⋮ Debiased magnitude-preserving ranking: learning rate and bias characterization ⋮ Extreme learning machine for ranking: generalization analysis and applications ⋮ The TreeRank Tournament algorithm for multipartite ranking ⋮ Elicitability of Instance and Object Ranking ⋮ Generalization bounds for metric and similarity learning

Cites Work

This page was built for publication: Ranking and empirical minimization of \(U\)-statistics