TY - GEN
T1 - Piecewise constant prediction
AU - Ordentlich, Erik
AU - Weinberger, Marcelo J.
AU - Wu, Yihong
PY - 2012
Y1 - 2012
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84867552929&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84867552929&partnerID=8YFLogxK
U2 - 10.1109/ISIT.2012.6284688
DO - 10.1109/ISIT.2012.6284688
M3 - Conference contribution
AN - SCOPUS:84867552929
SN - 9781467325790
T3 - IEEE International Symposium on Information Theory - Proceedings
SP - 880
EP - 884
BT - 2012 IEEE International Symposium on Information Theory Proceedings, ISIT 2012
T2 - 2012 IEEE International Symposium on Information Theory, ISIT 2012
Y2 - 1 July 2012 through 6 July 2012
ER -