Twice universal linear prediction of individual sequences

A. C. Singer, M. Feder

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We present a «twice universal» linear prediction algorithm over the unknown parameters and model orders, in which the sequentially accumulated square prediction error is as good as any linear predictor of order up to some M, for any individual sequence. The extra loss comprises of a parameter «redundancy» term proportional to (p/2)n-1/ln(n), and a model order «redundancy» term proportional to n-1/ln(p), where p, is the model order we compare with, and n is the data length. The computational complexity of the algorithm is about the complexity of a recursive least squares (RLS) linear predictor of order M.

Original languageEnglish (US)
Title of host publicationProceedings - 1998 IEEE International Symposium on Information Theory, ISIT 1998
Pages135
Number of pages1
DOIs
StatePublished - 1998
Externally publishedYes
Event1998 IEEE International Symposium on Information Theory, ISIT 1998 - Cambridge, MA, United States
Duration: Aug 16 1998Aug 21 1998

Publication series

NameIEEE International Symposium on Information Theory - Proceedings
ISSN (Print)2157-8095

Other

Other1998 IEEE International Symposium on Information Theory, ISIT 1998
Country/TerritoryUnited States
CityCambridge, MA
Period8/16/988/21/98

ASJC Scopus subject areas

  • Theoretical Computer Science
  • Information Systems
  • Modeling and Simulation
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'Twice universal linear prediction of individual sequences'. Together they form a unique fingerprint.

Cite this