A Strong Version of the Redundancy-Capacity Theorem of Universal Coding

Neri Merhav, Meir Feder

Research output: Contribution to journalArticlepeer-review

83 Scopus citations

Abstract

The capacity of the channel induced by a given class of sources is well known to be an attainable lower bound on the redundancy of universal codes with respect to this class, both in the minimax sense and in the Bayesian (maximin) sense. We show that this capacity is essentially a lower bound also in a stronger sense, that is, for “most” sources in the class. This result extends Rissanen's lower bound for parametric families. We demonstrate the applicability of this result in several examples, e.g., parametric families with growing dimensionality, piecewise-fixed sources, arbitrarily varying sources, and noisy samples of learnable functions. Finally, we discuss implications of our results to statistical inference.

Original languageEnglish
Pages (from-to)714-722
Number of pages9
JournalIEEE Transactions on Information Theory
Volume41
Issue number3
DOIs
StatePublished - May 1995

Funding

FundersFunder number
Israel Academy of Sciences and Humanities

    Keywords

    • Universal coding
    • arbitrarily varying sources
    • channel capacity
    • minimax redundancy
    • minimum description length
    • random coding

    Fingerprint

    Dive into the research topics of 'A Strong Version of the Redundancy-Capacity Theorem of Universal Coding'. Together they form a unique fingerprint.

    Cite this