Epsilon Entropy of Gaussian Processes
Posner, Edward C. ; Rodemich, Eugene R. ; Rumsey, Howard
Ann. Math. Statist., Tome 40 (1969) no. 6, p. 1272-1296 / Harvested from Project Euclid
This paper shows that the epsilon entropy of any mean-continuous Gaussian process on $L_2\lbrack 0, 1 \rbrack$ is finite for all positive $\epsilon$. The epsilon entropy of such a process is defined as the infimum of the entropies of all partitions of $L_2\lbrack 0, 1 \rbrack$ by measurable sets of diameter at most $\epsilon$, where the probability measure on $L_2$ is the one induced by the process. Fairly tight upper and lower bounds are found as $\epsilon \rightarrow 0$ for the epsilon entropy in terms of the eigenvalues of the process.
Publié le : 1969-08-14
Classification: 
@article{1177697502,
     author = {Posner, Edward C. and Rodemich, Eugene R. and Rumsey, Howard},
     title = {Epsilon Entropy of Gaussian Processes},
     journal = {Ann. Math. Statist.},
     volume = {40},
     number = {6},
     year = {1969},
     pages = { 1272-1296},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1177697502}
}
Posner, Edward C.; Rodemich, Eugene R.; Rumsey, Howard. Epsilon Entropy of Gaussian Processes. Ann. Math. Statist., Tome 40 (1969) no. 6, pp.  1272-1296. http://gdmltest.u-ga.fr/item/1177697502/