Introduction Deterministic computer simulations of physical phenomena are becoming widely used in science and engineering. Computers are used to describe the flow of air over an airplane wing, combustion of gasses in a flame, behavior of a metal structure under stress, safety of a nuclear reactor, and so on. Some of the most widely used computer models, and the ones that lead us to work in this area, arise in the design of the semiconductors used in the computers themselves. A process simulator starts with a data structure representing an unprocessed piece of silicon and simulates the steps such as oxidation, etching and ion injection that produce a semiconductor device such as a transistor. A device simulator takes a description of such a device and simulates the flow of current through it under varying conditions to determine properties of the device such as its switching speed and the critical voltage at which it switches. A circuit simulator takes a list of devices and the

. It is shown that Bayesian inference from data modeled by a mixture distribution can feasibly be performed via Monte Carlo simulation. This method exhibits the true Bayesian predictive distribution, implicitly integrating over the entire underlying parameter space. An infinite number of mixture components can be accommodated without difficulty, using a prior distribution for mixing proportions that selects a reasonable subset of components to explain any finite training set. The need to decide on a "correct" number of components is thereby avoided. The feasibility of the method is shown empirically for a simple classification task. Introduction Mixture distributions [8, 20] are an appropriate tool for modeling processes whose output is thought to be generated by several different underlying mechanisms, or to come from several different populations. One aim of a mixture model analysis may be to identify and characterize these underlying "latent classes" [2, 7], either for some scient...

We present a general approach to model selection and regularization that exploits unlabeled data to adaptively control hypothesis complexity in supervised learning tasks. The idea is to impose a metric structure on hypotheses by determining the discrepancy between their predictions across the distribution of unlabeled data. We show how this metric can be used to detect untrustworthy training error estimates, and devise novel model selection strategies that exhibit theoretical guarantees against over-tting (while still avoiding under- tting). We then extend the approach to derive a general training criterion for supervised learning|yielding an adaptive regularization method that uses unlabeled data to automatically set regularization parameters. This new criterion adjusts its regularization level to the specic set of training data received, and performs well on a variety of regression and conditional density estimation tasks. The only proviso for these methods is that s...

The author proposes a general method for evaluating the fit of a model for functional data. His approach consists of embedding the proposed model into a larger family of models, assuming the true process generating the data is within the larger family, and then computing a posterior distribution for the Kullback-Leibler distance between the true and the proposed models. The technique is illustrated on biomechanical data reported by Ramsay et al. (1995). It is developed in detail for hierarchical polynomial models such as those found in Lindley & Smith (1972), and is also generally applicable to longitudinal data analysis where polynomials are fit to many individuals. R ESUM E L'auteur propose une methode generale pour juger de l'adequation d'un modele pour donn ees fonctionnelles. Son approche consiste a plonger le modele envisage dans une classe plus vaste de modeles dont un des membres est censegenerer les donnees, puis acalculer une loi a posteriori pour la distance de Kullback...