On context-tree prediction of individual sequences
J Ziv, N Merhav - IEEE transactions on information theory, 2007 - ieeexplore.ieee.org
Motivated by the evident success of context-tree based methods in lossless data
compression, we explore, in this correspondence, methods of the same spirit in universal
prediction of individual sequences. By context-tree prediction, we refer to a family of
prediction schemes, where at each time instant t, after having observed all outcomes of the
data sequence x 1,..., x t-1, but not yet xt, the prediction is based on a" context"(or a state)
that consists of the k most recent past outcomes x tk,..., x t-1, where the choice of k may …
compression, we explore, in this correspondence, methods of the same spirit in universal
prediction of individual sequences. By context-tree prediction, we refer to a family of
prediction schemes, where at each time instant t, after having observed all outcomes of the
data sequence x 1,..., x t-1, but not yet xt, the prediction is based on a" context"(or a state)
that consists of the k most recent past outcomes x tk,..., x t-1, where the choice of k may …
Showing the best result for this search. See all results
