ML Anthology

Asymptotic Bias in Information Estimates and the Exponential (Bell) Polynomials

Jonathan D. Victor
NeCo 2001 pp. 2797-2804
doi:10.1162/089976600300014728 /neco/2001/victor2001neco-asymptotic/

Abstract

We present a new derivation of the asymptotic correction for bias in the estimate of information from a finite sample. The new derivation reveals a relationship between information estimates and a sequence of polynomials with combinatorial significance, the exponential (Bell) polynomials, and helps to provide an understanding of the form and behavior of the asymptotic correction for bias.

NeCo Semantic Scholar

Cite

Text

Victor. "Asymptotic Bias in Information Estimates and the Exponential (Bell) Polynomials." Neural Computation, 2001. doi:10.1162/089976600300014728

Markdown

[Victor. "Asymptotic Bias in Information Estimates and the Exponential (Bell) Polynomials." Neural Computation, 2001.](https://mlanthology.org/neco/2001/victor2001neco-asymptotic/) doi:10.1162/089976600300014728

BibTeX

@article{victor2001neco-asymptotic,
  title     = {{Asymptotic Bias in Information Estimates and the Exponential (Bell) Polynomials}},
  author    = {Victor, Jonathan D.},
  journal   = {Neural Computation},
  year      = {2001},
  pages     = {2797-2804},
  doi       = {10.1162/089976600300014728},
  volume    = {12},
  url       = {https://mlanthology.org/neco/2001/victor2001neco-asymptotic/}
}