Abstract
dc:descriptionFinally, we conclude the thesis by investigating the competitive prediction problem in a probabilistic setting. Here we investigate a particular algorithm and show that this algorithm is universal such that it asymptotically achieves the performance of the best predictor for Gaussian AR sources with unknown order up to some maximal order M.
Degree
thesis:*- Name thesis:degree_name
- Ph.D.
- Level thesis:degree_level
- Dissertation
- Discipline thesis:degree_discipline
- Electrical Engineering
- Grantor
- University of Illinois at Urbana-Champaign
- Year dc:date
- 2015
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Kozat, Suleyman Serdar
- Contributors dc:contributor
-
- Singer, Andrew C.
Subjects
dc:subject × 1Rights
- Language dc:language
- eng
Identifiers
dc:identifier.*- Identifier
- (MiAaPQ)AAI3160907
- OAI identifier oai:identifier
- oai:www.ideals.illinois.edu:2142/80892