Referenced Items are not available for this document.
We address the problem of online prediction for time series. We show that any universal code (or a universal data compressor) can be used as a basis for constructing asymptotically optimal methods for this problem for a certain class of stationary and ergodic processes.
Published in:
Information Theory, IEEE Transactions on
(Volume:55
,
Issue:
9
)
Date of Publication: Sept. 2009
- Page(s):
- 4309 - 4315
- ISSN :
- 0018-9448
- INSPEC Accession Number:
- 10828921
- Digital Object Identifier :
- 10.1109/TIT.2009.2025546
- Product Type:
- Journals & Magazines
- Date of Current Version :
- 18 August 2009
- Issue Date :
- Sept. 2009
- Sponsored by :
- IEEE Information Theory Society
About IEEE Xplore | Contact | Help | Terms of Use | Nondiscrimination Policy | Site Map | Privacy & Opting Out of Cookies
A not-for-profit organization, IEEE is the world's largest professional association for the advancement of technology.
© Copyright 2013 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.
