Large Deviations for Empirical Entropies of Gibbsian sources
نویسندگان
چکیده
The entropy of an ergodic finite-alphabet process can be computed from a single typical sample path x1 using the entropy of the k-block empirical probability and letting k grow with n roughly like logn. We further assume that the distribution of the process is a g-measure with respect to a continuous and regular g-function. We prove large deviation principles for conditional, non-conditional and relative k(n)-block empirical entropies.
منابع مشابه
Large deviations and the equivalence of ensembles for Gibbsian particle systems with superstable interaction
For Gibbsian systems of particles in R a, we investigate large deviations of the translation invariant empirical fields in increasing boxes. The particle interaction is given by a superstable, regular pair potential. The large deviation principle is established for systems with free or periodic boundary conditions and, under a stronger stability hypothesis on the potential, for systems with tem...
متن کاملar X iv : m at h / 04 06 08 3 v 3 [ m at h . PR ] 1 7 Ju n 20 05 Large deviations for empirical entropies of g - measures
The entropy of an ergodic finite-alphabet process can be computed from a single typical sample path x1 using the entropy of the k-block empirical probability and letting k grow with n roughly like logn. We further assume that the distribution of the process is a g-measure. We prove large deviation principles for conditional, non-conditional and relative k(n)-block empirical entropies.
متن کاملOn Approximate Pattern Matching for a Class of Gibbs Random Fields
We prove an exponential approximation for the law of approximate occurrence of typical patterns for a class of Gibbsian sources on the lattice Z, d ≥ 2. From this result, we deduce a law of large numbers and a large deviation result for the the waiting time of distorted patterns. Key-words: Gibbs measures, approximate matching, exponential law, lossy data compression, law of large numbers, larg...
متن کاملPercolation, Path Large Deviations and Weakly Gibbs States
We present a unified approach to establishing the Gibbsian character of a wide class of non-Gibbsian states, arising in the Renormalisation Group theory. Inside the realm of the Pirogov–Sinai theory for lattice spin systems, we prove that RG transformations applied to low temperature phases give rise to weakly Gibbsian measures. In other words, we show that the Griffiths–Pearce–Israel scenario ...
متن کاملA Gibbsian Kohonen Network for Online Arabic Character Recognition
The purpose of this study is to investigate handwritten online character recognition by Kohonen neural networks which learn class conditional Gibbs densities from training samples. The characters are represented by histograms (empirical distributions) of features. The Kohonen network learning algorithm implements a gradient ascent which maximizes an entropy criterion under constraints. Using a ...
متن کامل