In this paper, we investigate various connections between wavelet shrinkage methods in image processing and Bayesian estimation using Generalized Gaussian priors. We present fundamental properties of the shrinkage rules implied by Generalized Gaussian and other heavy-tailed priors. This allows us to show a simple relationship between differentiability of the log-prior at zero and the sparsity of the estimates, as well as an equivalence between universal thresholding schemes and Bayesian estimation using a certain Generalized Gaussian prior.

Abstruct-The problem of predicting the next outcome of an individual binary sequence using finite memory, is considered. The finite-state predictability of an infinite sequence is defined as the minimum fraction of prediction errors that can be made by any finite-state (FS) predictor. It is proved that this FS pre-dictability can be attained by universal sequential prediction schemes. Specifically, an efficient prediction procedure based on the incremental parsing procedure of the Lempel-Ziv data com-pression algorithm is shown to achieve asymptotically the FS predictability. Finally, some relations between compressibility and predictability are pointed out, and the predictability is proposed as an additional measure of the complexity of a sequence. Index Terms-Predictability, compressibility, complexity, fi-nite-state machines, Lempel- Ziv algorithm.

We describe a sequential universal data compression procedure for binary tree sources that performs the "double mixture." Using a context tree, this method weights in an efficient recursive way the coding distributions corresponding to all bounded memory tree sources, and achieves a desirable coding distribution for tree sources with an unknown model and unknown parameters. Computational and storage complexity of the proposed procedure are both linear in the source sequence length. We derive a natural upper bound on the cumulative redundancy of our method for individual sequences. The three terms in this bound can be identified as coding, parameter, and model redundancy. The bound holds for all source sequence lengths, not only for asymptotically large lengths. The analysis that leads to this bound is based on standard techniques and turns out to be extremely simple. Our upper bound on the redundancy shows that the proposed context-tree weighting procedure is optimal in the sense that it achieves the Rissanen (1984) lower bound.

This paper consists of an overview on universal prediction from an information-theoretic perspective. Special attention is given to the notion of probability assignment under the selfinformation loss function, which is directly related to the theory of universal data compression.

this paper, we confine ourselves to the former issue, and refer the interested reader to Li and Abe (1996), which deals with the latter issue

Abstract-In the absence of knowledge of the true density function, Bayesian models take the joint density function for a sequence of n random variables to be an average of densities with respect to a prior. We examine the relative entropy distance D,, between the true density and the Bayesian density and show that the asymptotic distance is (d/2Xlogn)+ c, where d is the dimension of the parameter vector. Therefore, the relative entropy rate D,,/n converges to zero at rate (logn)/n. The constant c, which we explicitly identify, depends only on the prior density function and the Fisher information matrix evaluated at the true parameter value. Consequences are given for density estima-tion, universal data compression, composite hypothesis testing, and stock-market portfolio selection. 1.

Genetic programming is distinguished from other evolutionary algorithms in that it uses tree representations of variable size instead of linear strings of fixed length. The flexible representation scheme is very important because it allows the underlying structure of the data to be discovered automatically. One primary difficulty, however, is that the solutions may grow too bigwithout any improvement oftheir generalization ability. In this article we investigate the fundamental relationship between the performance and complexity of the evolved structures. The essence of the parsimony problem is demonstrated empirically by analyzing error landscapes of programs evolved for neural network synthesis. We consider genetic programming as a statistical inference problem and apply the Bayesian modelcomparison framework to introduce a class of fitness functions with error and complexity terms. An adaptive learning method is then presented that automatically balances the model-complexity factor to evolve parsimonious programs without losing the diversity of the population needed for achieving the desired training accuracy. The effectiveness of this approach is empirically shown on the induction of sigma-pi neural networks for solving a real-world medical diagnosis problem as well as benchmark tasks.

Computation at levels beyond storage and transmission of information appears in physical systems at phase transitions. We investigate this phenomenon using minimal computational models of dynamical systems that undergo a transition to chaos as a function of a nonlinearity parameter. For period-doubling and band-merging cascades, we derive expressions for the entropy, the interdependence of-machine complexity and entropy, and the latent complexity of the transition to chaos. At the transition deterministic finite automaton models diverge in size. Although there is no regular or context-free Chomsky grammar in this case, we give finite descriptions at the higher computational level of context-free Lindenmayer systems. We construct a restricted indexed context-free grammar and its associated one-way nondeterministic nested stack automaton for the cascade limit language. This analysis of a family of dynamical systems suggests a complexity theoretic description of phase transitions based on the informational diversity and computational complexity of observed data that is independent of particular system control parameters. The approach gives a much more refined picture of the architecture of critical states than is available via

LOCO-I (LOw COmplexity L0ssless COmpression for Images) is a novel lossless compression algorithm for continuous-tone images which combines the simplicity of Huffman coding with the compression potential of context models, thus "enjoying the best of both worlds." The algorithm is based on a simple fixed context model, which approaches the capability of the nmre complex universal context modeling techniques for capturing high-order dependencies. The model is tuned for efficient performance in conjunction with a collection of (context-conditioned) Huffman codes, which is realized with an adaptive, symbol-wise, Golomb-Rice code. LOC0-I attains, in one pass, and without recourse to the higher complexity arithmetic coders, compression ratios similar or superior to those obtained with state-of-the-art schemes based on arittnetic coding. In fact, LOCO-I is being considered by the ISO committee as a replacement for the current lossless standard in low-complexity applications.

In this paper, we present some general results determining minimax bounds on statistical risk for density estimation based on certain information-theoretic considerations. These bounds depend only on metric entropy conditions and are used to identify the minimax rates of convergence.