General classes of Bayesian lower bounds for outage error probability and MSE

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Scopus citations

Abstract

In this paper, new classes of lower bounds on the outage error probability and on the minimum mean-square-error (MSE) in Bayesian parameter estimation are proposed. The outage error probability and the MSE are important criteria in parameter estimation. However, computation of these terms is usually not tractable. The proposed outage error probability class of lower bounds is derived using reverse Hölder inequality. This class is utilized to derive a new class of Bayesian MSE bounds. It is shown that the tightest bound from the proposed class is achieved by the generalized maximum a-posteriori probability (MAP) estimation. In addition, for unimodal symmetric conditional probability density functions, the tightest MSE bound in this class coincides with the minimum MSE (MMSE) obtained by the conditional expectation estimator. It is proved that the tightest MSE bound in this class is always tighter than the Ziv-Zakai lower bounds.

Original languageEnglish
Title of host publication2009 IEEE/SP 15th Workshop on Statistical Signal Processing, SSP '09
Pages69-72
Number of pages4
DOIs
StatePublished - 25 Dec 2009
Event2009 IEEE/SP 15th Workshop on Statistical Signal Processing, SSP '09 - Cardiff, United Kingdom
Duration: 31 Aug 20093 Sep 2009

Publication series

NameIEEE Workshop on Statistical Signal Processing Proceedings

Conference

Conference2009 IEEE/SP 15th Workshop on Statistical Signal Processing, SSP '09
Country/TerritoryUnited Kingdom
CityCardiff
Period31/08/093/09/09

Keywords

  • Bayesian parameter estimation
  • Maximum a-posteriori probability (MAP)
  • Mean-square-error (MSE)
  • Performance lower bounds
  • Probability of outage error

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Applied Mathematics
  • Signal Processing
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'General classes of Bayesian lower bounds for outage error probability and MSE'. Together they form a unique fingerprint.

Cite this