Probability estimation in the rare-events regime

Research output: Contribution to journalArticlepeer-review

20 Scopus citations

Abstract

We address the problem of estimating the probability of an observed string that is drawn i.i.d. from an unknown distribution. Motivated by models of natural language, we consider the regime in which the length of the observed string and the size of the underlying alphabet are comparably large. In this regime, the maximum likelihood distribution tends to overestimate the probability of the observed letters, so the Good-Turing probability estimator is typically used instead. We show that when used to estimate the sequence probability, the Good-Turing estimator is not consistent in this regime. We then introduce a novel sequence probability estimator that is consistent. This estimator also yields consistent estimators for other quantities of interest and a consistent universal classifier.

Original languageEnglish (US)
Article number5773059
Pages (from-to)3207-3229
Number of pages23
JournalIEEE Transactions on Information Theory
Volume57
Issue number6
DOIs
StatePublished - Jun 2011

All Science Journal Classification (ASJC) codes

  • Information Systems
  • Computer Science Applications
  • Library and Information Sciences

Keywords

  • Classification
  • entropy estimation
  • large alphabets
  • large number of rare events (LNRE)
  • natural language
  • probability estimation

Fingerprint

Dive into the research topics of 'Probability estimation in the rare-events regime'. Together they form a unique fingerprint.

Cite this