An approach to the problem of linear prediction is discussed that is based on recent developments in the universal coding and computational learning theory literature. This development provides a novel perspective on the adaptive filtering problem, and represents a significant departure from traditional adaptive filtering methodologies. In this context, we demonstrate a sequential algorithm for linear prediction whose accumulated squared prediction error, for every possible sequence, is asymptotically as small as the best fixed linear predictor for that sequence.

Original languageEnglish (US)
Number of pages1
JournalIEEE International Symposium on Information Theory - Proceedings
StatePublished - 2000
Event2000 IEEE International Symposium on Information Theory - Serrento, Italy
Duration: Jun 25 2000Jun 30 2000

ASJC Scopus subject areas

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


Dive into the research topics of 'Universal linear least-squares prediction'. Together they form a unique fingerprint.

Cite this