Semiparametric model and superefficiency in blind deconvolution

L. Q. Zhang, S. Amari, A. Cichocki

Research output: Contribution to journalArticlepeer-review

10 Citations (Scopus)

Abstract

In this paper, we study convergence and efficiency of the batch estimator and natural gradient algorithm for blind deconvolution. First, the blind deconvolution problem is formulated in the framework of a semiparametric model, and a family of estimating functions is derived for blind deconvolution. To improve the learning efficiency of the online algorithm, explicit standardized estimating functions are given and within this framework the superefficiency of batch learning and online natural gradient learning is proven.

Original languageEnglish
Pages (from-to)2535-2553
Number of pages19
JournalSignal Processing
Volume81
Issue number12
DOIs
Publication statusPublished - Dec 2001
Externally publishedYes

Keywords

  • Blind deconvolution
  • Estimating function
  • Independent component analysis
  • Natural gradient
  • Semiparametric model
  • Superefficiency

Fingerprint

Dive into the research topics of 'Semiparametric model and superefficiency in blind deconvolution'. Together they form a unique fingerprint.

Cite this