Bartlett, PeterLugosi, GáborUniversitat Pompeu Fabra. Departament d'Economia i Empresa2020-05-252020-05-251998-02-01Statistics and Probability Letters, 44, (1999), pp. 55-62http://hdl.handle.net/10230/905We derive a new inequality for uniform deviations of averages from their means. The inequality is a common generalization of previous results of Vapnik and Chervonenkis (1974) and Pollard (1986). Using the new inequality we obtain tight bounds for empirical loss minimization learning.application/pdfengL'accés als continguts d'aquest document queda condicionat a l'acceptació de les condicions d'ús establertes per la següent llicència Creative Commonsinfo:eu-repo/semantics/workingPapervapnik-chervonenkis inequalityuniform laws of large numbersempirical riskminimizationStatistics, Econometrics and Quantitative Methodsinfo:eu-repo/semantics/openAccess