Title :
Piecewise constant prediction
Author :
Ordentlich, Erik ; Weinberger, Marcelo J. ; Wu, Yihong
Author_Institution :
Inf. Theor. Res., Hewlett-Packard Labs., Palo Alto, CA, USA
Abstract :
Minimax prediction of binary sequences is investigated for cases in which the predictor is forced to issue a piecewise constant prediction. The minimax strategy is characterized for Hamming loss whereas, for logarithmic loss, an asymptotically minimax strategy which achieves the leading term of the asymptotic minimax redundancy, is proposed. The average redundancy case is also analyzed for i.i.d. distributions. The piecewise constant prediction paradigm may be of relevance to resource constrained settings.
Keywords :
Hamming codes; binary sequences; losses; minimax techniques; piecewise constant techniques; prediction theory; Hamming loss; asymptotic minimax redundancy; asymptotically minimax strategy; binary sequence; i.i.d. distribution; logarithmic loss; piecewise constant prediction paradigm; resource constrained setting; Data compression; Delay; Encoding; Games; Prediction algorithms; Redundancy;
Conference_Titel :
Information Theory Proceedings (ISIT), 2012 IEEE International Symposium on
Conference_Location :
Cambridge, MA
Print_ISBN :
978-1-4673-2580-6
Electronic_ISBN :
2157-8095
DOI :
10.1109/ISIT.2012.6284688
