Distribution-free performance bounds for potential function rules

DOI10.1109/TIT.1979.1056087MaRDI QIDQ3870168zbMATH OpenOpenAlexFDO

Authors T. J. Wagner, Luc Devroye

Publication date 1979

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/tit.1979.1056087

zbMATH Keywords

discrimination rulesdistribution-free performance boundshistogram rulespotential function rulestwo-step rules

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30)

Cited in

(27)

• OCReP: an optimally conditioned regularization for pseudoinversion based neural training
• Oracle inequalities for cross-validation type procedures
• A tight upper bound on the generalization error of feedforward neural networks
• A selective overview of deep learning
• Uncertainty learning of rough set-based prediction under a holistic framework
• Learning theory: stability is sufficient for generalization and necessary and sufficient for consistency of empirical risk minimization
• Theory of Classification: a Survey of Some Recent Advances
• Robustness and generalization
• Theoretical analysis of cross-validation for estimating the risk of the \(k\)-nearest neighbor classifier
• Universal Prediction Distribution for Surrogate Models
• Ten More Years of Error Rate Research
• Constructive reinforcement learning
• The big data newsvendor: practical insights from machine learning
• Algorithmic stability for adaptive data analysis
• Stability and optimization error of stochastic gradient descent for pairwise learning
• Concentration inequalities of the cross-validation estimator for empirical risk minimizer
• STABILITY RESULTS IN LEARNING THEORY
• Exact representation of the second-order moments for resubstitution and leave-one-out error estimation for linear discriminant analysis in the univariate heteroskedastic Gaussian model
• Stability is stable: connections between replicability, privacy, and adaptive generalization
• Multi-split conformal prediction via Cauchy aggregation
• Cross-validation on extreme regions
• Algorithmic stability implies training-conditional coverage for distribution-free prediction methods
• Optimization and learning with randomly compressed gradient updates
• Generalization bounds: perspectives from information theory and PAC-Bayes
• An exponential Efron-Stein inequality for L_q stable learning rules
• Stability via resampling: statistical problems beyond the real line
• A survey of cross-validation procedures for model selection

This page was built for publication: Distribution-free performance bounds for potential function rules

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3870168)