A generalized poor-verd error bound for multihypothesis testing

Po-Ning Chen*, Fady Alajaji

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

5 Scopus citations

Abstract

A lower bound on the minimum error probability for multihypothesis testing is established. The bound, which is expressed in terms of the cumulative distribution function of the tilted posterior hypothesis distribution given the observation with tilting parameter $\theta \geq 1$, generalizes an earlier bound due the Poor and Verd (1995). A sufficient condition is established under which the new bound (minus a multiplicative factor) provides the exact error probability asymptotically in $\theta $. Examples illustrating the new bound are also provided.

Original languageEnglish
Article number6121979
Pages (from-to)311-316
Number of pages6
JournalIEEE Transactions on Information Theory
Volume58
Issue number1
DOIs
StatePublished - 1 Jan 2012

Keywords

  • Channel reliability function
  • converse channel coding theorems
  • hypothesis testing
  • maximum-a-posteriori estimation
  • probability of error

Fingerprint Dive into the research topics of 'A generalized poor-verd error bound for multihypothesis testing'. Together they form a unique fingerprint.

Cite this