A Simple Lemma on Greedy Approximation in Hilbert Space and Convergence Rates for Projection Pursuit Regression and Neural Network Training
Jones, Lee K.
Ann. Statist., Tome 20 (1992) no. 1, p. 608-613 / Harvested from Project Euclid
Text on Project Euclid
PDF
Alt PDF
A general convergence criterion for certain iterative sequences in Hilbert space is presented. For an important subclass of these sequences, estimates of the rate of convergence are given. Under very mild assumptions these results establish an $O(1/ \sqrt n)$ nonsampling convergence rate for projection pursuit regression and neural network training; where $n$ represents the number of ridge functions, neurons or coefficients in a greedy basis expansion.
Publié le : 1992-03-14
Classification:  Projection pursuit,  greedy expansion,  neural network,  62H99 
@article{1176348546,
     author = {Jones, Lee K.},
     title = {A Simple Lemma on Greedy Approximation in Hilbert Space and Convergence Rates for Projection Pursuit Regression and Neural Network Training},
     journal = {Ann. Statist.},
     volume = {20},
     number = {1},
     year = {1992},
     pages = { 608-613},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176348546}
}

Jones, Lee K. A Simple Lemma on Greedy Approximation in Hilbert Space and Convergence Rates for Projection Pursuit Regression and Neural Network Training. Ann. Statist., Tome 20 (1992) no. 1, pp.  608-613. http://gdmltest.u-ga.fr/item/1176348546/