ML Anthology

Rate of Convergence in Density Estimation Using Neural Networks

Dharmendra S. Modha, Elias Masry
NeCo 1996 pp. 1107-1122
doi:10.1162/NECO.1996.8.5.1107 /neco/1996/modha1996neco-rate/

Abstract

Given N i.i.d. observations XiNi=1 taking values in a compact subset of Rd, such that p* denotes their common probability density function, we estimate p* from an exponential family of densities based on single hidden layer sigmoidal networks using a certain minimum complexity density estimation scheme. Assuming that p* possesses a certain exponential representation, we establish a rate of convergence, independent of the dimension d, for the expected Hellinger distance between the proposed minimum complexity density estimator and the true underlying density p*.

NeCo Semantic Scholar

Cite

Text

Modha and Masry. "Rate of Convergence in Density Estimation Using Neural Networks." Neural Computation, 1996. doi:10.1162/NECO.1996.8.5.1107

Markdown

[Modha and Masry. "Rate of Convergence in Density Estimation Using Neural Networks." Neural Computation, 1996.](https://mlanthology.org/neco/1996/modha1996neco-rate/) doi:10.1162/NECO.1996.8.5.1107

BibTeX

@article{modha1996neco-rate,
  title     = {{Rate of Convergence in Density Estimation Using Neural Networks}},
  author    = {Modha, Dharmendra S. and Masry, Elias},
  journal   = {Neural Computation},
  year      = {1996},
  pages     = {1107-1122},
  doi       = {10.1162/NECO.1996.8.5.1107},
  volume    = {8},
  url       = {https://mlanthology.org/neco/1996/modha1996neco-rate/}
}