We show how to construct empirical models directly from experimental low-dimensional time series. Specfically, we examine data from a string experiment and use MDL to contruct an "op timial" empirical model and show how this empirical model can be syncronized to the chaotic experimental data. Such empirical models can then used for process control, monitoring, and non-destructive testing. For a reference, see .
Asymptotic equipartition property in source coding
Sergio Verdu, Princeton email@example.com
Abstract not available.
Sequential Prediction and Ranking in Universal Context Modeling and Data Compression
Marcelo Weinberger, HP Labs Palo Alto firstname.lastname@example.org
We investigate the use of prediction as a means of reducing the model cost in lossless data compression. We provide a formal justification to the combination of this widely accepted tool with a universal code based on context modeling, by showing that a combined scheme may result in faster convergence rate to the source entropy. In deriving the main result, we develop the concept of sequential ranking, which can be seen as a generalization of sequential prediction, and we study its combinatorial and probabilistic properties. For a reference, see .