find that an ME smoothing method proposed to us by Lafferty [1] performs as well as or better than all other algorithms under consideration. This general and efficient method involves using a Gaussian prior on the parame-ters of the model and selecting maximum a posteriori instead of maximum likelihood

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

a very big flexibility. Support Vector Machines (SVM's) and Gaussian processes are two examples of such models. In this technical report I present a model in which the dimension of the feature space remains finite, and where a Bayesian approach is used to train the model with Gaussian priors

Abstract not found

Abstract not found

This paper describes the sale and optimal regulation of a sequence of public utilities, where monitoring of regulatory compliance is costly. The government is concerned with the revenue raised by successive privatizations as well as the standard objective of efficiency in production. The costs of monitoring are private information to the government. At each stage in the sequence of privatizations the public Bayes updates it s distribution of posterior beliefs over the governments regulatory enforcement strategy. The government knows that this learning is taking place and chooses the time path of monitoring levels accordingly.

We show how the regularization used for classification can be seen from the MDL viewpoint as a Gaussian prior on weights. We consider the problem of transmitting classification labels; we select as our model class logistic regression with perfect precision where we specify a weight for each feature

A "partially improper" Gaussian prior is considered for Bayesian inference in logistic regression. This includes generalized smoothing spline priors that are used for nonparametric inference about the logit, and also priors that correspond to generalized random effect models. Necessary

Statistical image reconstruction methods based on maximum a posteriori (MAP) principle have been developed for emission tomography. The prior distribution of the unknown image plays an important role in MAP reconstruction. The most commonly used prior are Gaussian priors, whose logarithm has a

Random probability measures are the main tool for Bayesian nonparametric inference, with their laws acting as prior distributions. Many well-known priors used in practice admit different, though equivalent, representations. In terms of computational convenience, stick-breaking representations stand