Joint universal lossy coding and identification of stationary mixing sources with general alphabets

Research output: Contribution to journalArticlepeer-review

Abstract

In this paper, we consider the problem of joint universal variable-rate lossy coding and identification for parametric classes of stationary β-mixing sources with general (Polish) alphabets. Compression performance is measured in terms of Lagrangians, while identification performance is measured by the variational distance between the true source and the estimated source. Provided that the sources are mixing at a sufficiently fast rate and satisfy certain smoothness and Vapnik-Chervonenkis (VC) learnability conditions, it is shown that, for bounded metric distortions, there exist universal schemes for joint lossy compression and identification whose Lagrangian redundancies converge to zero as √ Vn log n/n as the block length n tends to infinity, where Vn is the VC dimension of a certain class of decision regions defined by the n-dimensional marginal distributions of the sources; furthermore, for each n, the decoder can identify O(√ Vn log n/n-dimensional marginal of the active source up to a ball of radius O(√ Vn log n/n) in variational distance, eventually with probability one. The results are supplemented by several examples of parametric sources satisfying the regularity conditions.

Original languageEnglish (US)
Pages (from-to)1945-1960
Number of pages16
JournalIEEE Transactions on Information Theory
Volume55
Issue number5
DOIs
StatePublished - 2009

Keywords

  • Learning
  • Minimum-distance density estimation
  • Two-stage codes
  • Universal vector quantization
  • Vapnik-Chervonenkis (VC) dimension

ASJC Scopus subject areas

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

Fingerprint

Dive into the research topics of 'Joint universal lossy coding and identification of stationary mixing sources with general alphabets'. Together they form a unique fingerprint.

Cite this