Generalization and improvement to PPM's "blending"

Abstract

Summary form only given. The best-performing method in the data compression literature for computing probability estimates of sequences on-line using a suffix-tree model is the blending technique used by PPM. Blending can be viewed as a bottom-up recursive procedure for computing a mixture, barring one missing term for each level of the recursion, where a mixture is basically a weighted average of several probability estimates. The author shows the relative effectiveness of most combinations of mixture weighting functions and inheritance evaluation times. The results of a study on the value of using update exclusion, especially in models using state selection, are also sown.