Skip to main navigation Skip to search Skip to main content

Asymptotic bias in information estimates and the exponential (Bell) polynomials

  • Jonathan D. Victor

Research output: Contribution to journalArticlepeer-review

35 Scopus citations

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.

Original languageEnglish
Pages (from-to)2797-2804
Number of pages8
JournalNeural Computation
Volume12
Issue number12
DOIs
StatePublished - Dec 2000
Externally publishedYes

Fingerprint

Dive into the research topics of 'Asymptotic bias in information estimates and the exponential (Bell) polynomials'. Together they form a unique fingerprint.

Cite this