### 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 language | English (US) |
---|---|

Title of host publication | Proceedings - 1998 IEEE International Symposium on Information Theory, ISIT 1998 |

Number of pages | 1 |

DOIs | |

State | Published - Dec 1 1998 |

Externally published | Yes |

Event | 1998 IEEE International Symposium on Information Theory, ISIT 1998 - Cambridge, MA, United States Duration: Aug 16 1998 → Aug 21 1998 |

### Publication series

Name | IEEE International Symposium on Information Theory - Proceedings |
---|---|

ISSN (Print) | 2157-8095 |

### Other

Other | 1998 IEEE International Symposium on Information Theory, ISIT 1998 |
---|---|

Country | United States |

City | Cambridge, MA |

Period | 8/16/98 → 8/21/98 |

### 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

Singer, A. C., & Feder, M. (1998). Twice universal linear prediction of individual sequences. In

*Proceedings - 1998 IEEE International Symposium on Information Theory, ISIT 1998*[708726] (IEEE International Symposium on Information Theory - Proceedings). https://doi.org/10.1109/ISIT.1998.708726