Paper #376

Títol:

A sharp concentration inequality with applications

Autors:

Stéphane Boucheron, Gábor Lugosi i Pascal Massart

Data:

Abril 1999

Resum:

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.

Paraules clau:

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

Codis JEL:

C1

Àrea de Recerca:

Estadística, Econometria i Mètodes Quantitatius

Publicat a:

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

Descarregar el paper en format PDF