### Abstract

A simple on-line procedure is considered for the prediction of a binary-valued sequence in the setup introduced and studied by Weissman and Merhav [13], [14], where only side information is available for the algorithm. The (non-randomized) algorithm is based on a convex combination of several simple predictors. If the side information is also binary-valued (i.e. original sequence is corrupted by a binary sequence) and both processes are realizations of stationary and ergodic random processes then the average of the loss converges, almost surely, to that of the optimum, given by the Bayes predictor. An analog result is offered for the classification of binary processes.

Original language | English |
---|---|

Title of host publication | Proceedings - 2007 IEEE International Symposium on Information Theory, ISIT 2007 |

Pages | 2351-2355 |

Number of pages | 5 |

DOIs | |

Publication status | Published - Dec 1 2007 |

Event | 2007 IEEE International Symposium on Information Theory, ISIT 2007 - Nice, France Duration: Jun 24 2007 → Jun 29 2007 |

### Publication series

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

ISSN (Print) | 2157-8101 |

### Other

Other | 2007 IEEE International Symposium on Information Theory, ISIT 2007 |
---|---|

Country | France |

City | Nice |

Period | 6/24/07 → 6/29/07 |

### Fingerprint

### ASJC Scopus subject areas

- Theoretical Computer Science
- Information Systems
- Modelling and Simulation
- Applied Mathematics

### Cite this

*Proceedings - 2007 IEEE International Symposium on Information Theory, ISIT 2007*(pp. 2351-2355). [4557170] (IEEE International Symposium on Information Theory - Proceedings). https://doi.org/10.1109/ISIT.2007.4557170