Information-theoretic determination of minimax rates of convergence
Yang, Yuhong ; Barron, Andrew
Ann. Statist., Tome 27 (1999) no. 4, p. 1564-1599 / Harvested from Project Euclid
Text on Project Euclid
PDF
Alt PDF
We present some general results determining minimax bounds on statistical risk for density estimation based on certain information-theoretic considerations. These bounds depend only on metric entropy conditions and are used to identify the minimax rates of convergence.
Publié le : 1999-10-14
Classification:  Minimax risk,  density estimation,  metric entropy,  Kullback-Leibler distance,  62G07,  62B10,  62C20,  94A29 
@article{1017939142,
     author = {Yang, Yuhong and Barron, Andrew},
     title = {Information-theoretic determination of minimax rates of
			 convergence},
     journal = {Ann. Statist.},
     volume = {27},
     number = {4},
     year = {1999},
     pages = { 1564-1599},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1017939142}
}

Yang, Yuhong; Barron, Andrew. Information-theoretic determination of minimax rates of
			 convergence. Ann. Statist., Tome 27 (1999) no. 4, pp.  1564-1599. http://gdmltest.u-ga.fr/item/1017939142/