Boucheron, StéphaneLugosi, GáborMassart, PascalUniversitat Pompeu Fabra. Departament d'Economia i Empresa2017-07-262017-07-261999-04-01Random Structures and Algorithms, 16, (2000), pp. 277-292http://hdl.handle.net/10230/593We present a new general concentration-of-measure inequality and illustrate its power by applications in random combinatorics. The results find direct applications in some problems of learning theory.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/workingPaperconcentration of measurevapnik-chervonenkis dimensionlogarithmic sobolev inequalitieslongest monotone subsequencemodel selectionStatistics, Econometrics and Quantitative Methodsinfo:eu-repo/semantics/openAccess