Concentration inequalities for two-sample rank processes with application to bipartite ranking
From MaRDI portal
Publication:2233587
DOI10.1214/21-EJS1907zbMath1471.62356arXiv2104.02943OpenAlexW3202421026MaRDI QIDQ2233587
Nicolas Vayatis, Stéphan Clémençon, Myrto Limnios
Publication date: 11 October 2021
Published in: Electronic Journal of Statistics (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2104.02943
statistical learning theoryconcentration inequalitiesempirical risk minimizationgeneralization boundsbipartite rankingtwo-sample linear rank statisticsrank process
Inequalities; stochastic orderings (60E15) Learning and adaptive systems in artificial intelligence (68T05) Empirical decision procedures; empirical Bayes procedures (62C12) Nonparametric inference (62G99)
Cites Work
- Ranking data with ordinal labels: optimality and pairwise aggregation
- A statistical view of clustering performance through the theory of \(U\)-processes
- U-processes: Rates of convergence
- Overlaying classifiers: A practical approach to optimal scoring
- Some limit theorems for empirical processes (with discussion)
- An estimate on the supremum of a nice class of stochastic integrals and U-statistics
- The performance of kernel density functions in kernel distribution function estimation
- Sharper bounds for Gaussian and empirical processes
- A distribution-free theory of nonparametric regression
- Rates of strong uniform consistency for multivariate kernel density estimators. (Vitesse de convergence uniforme presque sûre pour des estimateurs à noyaux de densités multivariées)
- Weighted uniform consistency of kernel density estimators.
- Weak convergence and empirical processes. With applications to statistics
- Local Rademacher complexities and oracle inequalities in risk minimization. (2004 IMS Medallion Lecture). (With discussions and rejoinder)
- Ranking and empirical minimization of \(U\)-statistics
- A central limit theorem for two-sample U-processes
- Approximation Theorems of Mathematical Statistics
- Theory of Classification: a Survey of Some Recent Advances
- Asymptotic Statistics
- Tree-Based Ranking Methods
- The TreeRank Tournament algorithm for multipartite ranking
- Ranking with a P-Norm Push
- Subset Ranking Using Regression
- Asymptotically Most Powerful Rank-Order Tests
- Some New Estimates for Distribution Functions
- Asymptotic Normality of Simple Linear Rank Statistics Under Alternatives
- A Class of Statistics with Asymptotically Normal Distribution
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
