Paper #376

Título:

A sharp concentration inequality with applications

Autores:

Stéphane Boucheron, Gábor Lugosi y Pascal Massart

Data:

Abril 1999

Resumen:

We 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.

Palabras clave:

Concentration of measure, Vapnik-Chervonenkis dimension, logarithmic Sobolev inequalities, longest monotone subsequence, model selection

Códigos JEL:

C1

Área de investigación:

Estadística, Econometría y Métodos Cuantitativos

Publicado en:

Random Structures and Algorithms, 16, (2000), pp. 277-292

Descargar el paper en formato PDF