TY - GEN

T1 - Twice universal linear prediction of individual sequences

AU - Singer, A. C.

AU - Feder, M.

PY - 1998/12/1

Y1 - 1998/12/1

N2 - We present a «twice universal» linear prediction algorithm over the unknown parameters and model orders, in which the sequentially accumulated square prediction error is as good as any linear predictor of order up to some M, for any individual sequence. The extra loss comprises of a parameter «redundancy» term proportional to (p/2)n-1/ln(n), and a model order «redundancy» term proportional to n-1/ln(p), where p, is the model order we compare with, and n is the data length. The computational complexity of the algorithm is about the complexity of a recursive least squares (RLS) linear predictor of order M.

AB - We present a «twice universal» linear prediction algorithm over the unknown parameters and model orders, in which the sequentially accumulated square prediction error is as good as any linear predictor of order up to some M, for any individual sequence. The extra loss comprises of a parameter «redundancy» term proportional to (p/2)n-1/ln(n), and a model order «redundancy» term proportional to n-1/ln(p), where p, is the model order we compare with, and n is the data length. The computational complexity of the algorithm is about the complexity of a recursive least squares (RLS) linear predictor of order M.

UR - http://www.scopus.com/inward/record.url?scp=84890355584&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890355584&partnerID=8YFLogxK

U2 - 10.1109/ISIT.1998.708726

DO - 10.1109/ISIT.1998.708726

M3 - Conference contribution

AN - SCOPUS:84890355584

SN - 0780350006

SN - 9780780350007

T3 - IEEE International Symposium on Information Theory - Proceedings

BT - Proceedings - 1998 IEEE International Symposium on Information Theory, ISIT 1998

T2 - 1998 IEEE International Symposium on Information Theory, ISIT 1998

Y2 - 16 August 1998 through 21 August 1998

ER -