Concentration inequalities for two-sample rank processes with application to bipartite ranking
From MaRDI portal
Publication:2233587
Abstract: The ROC curve is the gold standard for measuring the performance of a test/scoring statistic regarding its capacity to discriminate between two statistical populations in a wide variety of applications, ranging from anomaly detection in signal processing to information retrieval, through medical diagnosis. Most practical performance measures used in scoring/ranking applications such as the AUC, the local AUC, the p-norm push, the DCG and others, can be viewed as summaries of the ROC curve. In this paper, the fact that most of these empirical criteria can be expressed as two-sample linear rank statistics is highlighted and concentration inequalities for collections of such random variables, referred to as two-sample rank processes here, are proved, when indexed by VC classes of scoring functions. Based on these nonasymptotic bounds, the generalization capacity of empirical maximizers of a wide class of ranking performance criteria is next investigated from a theoretical perspective. It is also supported by empirical evidence through convincing numerical experiments.
Recommendations
- Applications of concentration inequalities for statistical scoring and ranking problems
- Generalization bounds for the area under the ROC curve
- Adaptive estimation of the optimal ROC curve and a bipartite ranking algorithm
- Generalization performance of bipartite ranking algorithms with convex losses
- Bipartite ranking: a risk-theoretic perspective
Cites work
- scientific article; zbMATH DE number 4170917 (Why is no real title available?)
- scientific article; zbMATH DE number 5654889 (Why is no real title available?)
- scientific article; zbMATH DE number 47948 (Why is no real title available?)
- scientific article; zbMATH DE number 893887 (Why is no real title available?)
- scientific article; zbMATH DE number 3258670 (Why is no real title available?)
- A Class of Statistics with Asymptotically Normal Distribution
- A central limit theorem for two-sample U-processes
- A distribution-free theory of nonparametric regression
- A statistical view of clustering performance through the theory of U-processes
- An estimate on the supremum of a nice class of stochastic integrals and U-statistics
- Approximation Theorems of Mathematical Statistics
- Asymptotic Normality of Simple Linear Rank Statistics Under Alternatives
- Asymptotic Statistics
- Asymptotically Most Powerful Rank-Order Tests
- Bipartite ranking: a risk-theoretic perspective
- Generalization bounds for the area under the ROC curve
- Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
- Overlaying classifiers: A practical approach to optimal scoring
- Ranking and empirical minimization of \(U\)-statistics
- Ranking data with ordinal labels: optimality and pairwise aggregation
- Ranking the best instances
- Ranking with a P-Norm Push
- Rates of strong uniform consistency for multivariate kernel density estimators. (Vitesse de convergence uniforme presque sûre pour des estimateurs à noyaux de densités multivariées)
- Sharper bounds for Gaussian and empirical processes
- Some New Estimates for Distribution Functions
- Some limit theorems for empirical processes (with discussion)
- Subset Ranking Using Regression
- The performance of kernel density functions in kernel distribution function estimation
- The treerank tournament algorithm for multipartite ranking
- Theory of Classification: a Survey of Some Recent Advances
- Tree-Based Ranking Methods
- U-processes: Rates of convergence
- Weak convergence and empirical processes. With applications to statistics
- Weighted uniform consistency of kernel density estimators.
Cited in
(4)
This page was built for publication: Concentration inequalities for two-sample rank processes with application to bipartite ranking
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2233587)
