Characteristics of Normal Samples
Goodman, Victor
Ann. Probab., Tome 16 (1988) no. 4, p. 1281-1290 / Harvested from Project Euclid
A "law of large numbers" for the maximum of i.i.d. univariate normal random variables is extended to a general multivariate case. Let $\mathbf{Z}_i$ denote i.i.d. Banach space valued random variables with a centered Gaussian distribution. Let $\mathbf{K}$ denote the unit ball of the reproducing kernel Hilbert space. Then with probability 1, the maximum distance from the sample points $\mathbf{Z}_1, \mathbf{Z}_2,\ldots, \mathbf{Z}_n$ to the set $\sqrt{2 \log n} \mathbf{K}$ approaches zero. In addition, the sample forms epsilon nets for this set as $n$ tends to infinity.
Publié le : 1988-07-14
Classification:  Gaussian processes,  i.i.d. samples,  reproducing kernels,  cluster set,  60B11,  60D05,  60G15,  60B12,  60F10,  60F20
@article{1176991690,
     author = {Goodman, Victor},
     title = {Characteristics of Normal Samples},
     journal = {Ann. Probab.},
     volume = {16},
     number = {4},
     year = {1988},
     pages = { 1281-1290},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176991690}
}
Goodman, Victor. Characteristics of Normal Samples. Ann. Probab., Tome 16 (1988) no. 4, pp.  1281-1290. http://gdmltest.u-ga.fr/item/1176991690/