We propose a method for approximating integrated likelihoods in finite mixture models. We formulate the model in terms of the unobserved group memberships, z, and make them the variables of integration. The integral is then evaluated using importance sampling over the z. We propose an adaptive importance sampling function which is itself a mixture, with two types of component distributions, one concentrated and one diffuse. The more concentrated type of component serves the usual purpose of an importance sampling function, sampling mostly group assignments of high posterior probability. The less concentrated type of component allows for the importance sampling function to explore the space in a controlled way to find other, unvisited assignments with high posterior probability. Components are added adaptively, one at a time, to cover areas of high posterior probability not well covered by the current important sampling function. The method is called Incremental Mixture Importance Sampling (IMIS). IMIS is easy to implement and to monitor for convergence. It scales easily for higher dimensional

We propose prior probability models for variance-covariance matrices in order to address two important issues. First, the models allow a researcher to represent substantive prior information about the strength of correlations among a set of variables. Secondly, even in the absence of such information, the increased flexibility of the models mitigates dependence on strict parametric assumptions in standard prior models. For example, the model allows a posteriori different levels of uncertainty about correlations among different subsets of variables. We achieve this by including a clustering mechanism in the prior probability model. Clustering is with respect to variables and pairs of variables. Our approach leads to shrinkage towards a mixture structure implied by the clustering. We discuss appropriate posterior simulation schemes to implement posterior inference in the proposed models, including the evaluation of normalising constants that are functions of parameters of interest. The normalising constants result from the restriction that the correlation matrix be positive definite. We discuss examples based on simulated data, a stock return dataset and a population genetics dataset.

The mixture model likelihood function is invariant with respect to permutation of the components of the mixture. If functions of interest are permutation sensitive, as in classification applications, then interpretation of the likelihood function requires valid inequality constraints and a very large sample may be required to resolve ambiguities. If functions of interest are permutation invariant, as in prediction applications, then there are no such problems of interpretation. Contrary to assessments in some recent publications, simple and widely used Markov chain Monte Carlo (MCMC) algorithms with data augmentation reliably recover the entire posterior distribution. 1 1

this paper. The reason for the paradoxical complexity of the mixture model is due to the product structure of the likelihood function, L(` 1 ; : : : ; ` k jx 1 ; : : : ; xn ) =

This paper shows (i) improvements over state-of-the-art local feature recognition systems, (ii) how to formulate principled models for automatic local feature selection in object class recognition when there is little supervised data, and (iii) how to formulate sensible spatial image context models using a conditional random field for integrating local features and segmentation cues (superpixels). By adopting sparse kernel methods, Bayesian learning techniques and data association with constraints, the proposed model identifies the most relevant sets of local features for recognizing object classes, achieves performance comparable to the fully supervised setting, and obtains excellent results for image classification.

This paper proposes a new efficient merge-split sampler for both conjugate and nonconjugate Dirichlet process mixture (DPM) models. These Bayesian nonparametric models are usually fit using Markov chain Monte Carlo (MCMC) or sequential importance sampling (SIS). The latest generation of Gibbs and Gibbs-like samplers for both conjugate and nonconjugate DPM models effectively update the model parameters, but can have difficulty in updating the clustering of the data. To overcome this deficiency, merge-split samplers have been developed, but until now these have been limited to conjugate or conditionally-conjugate DPM models. This paper proposes a new MCMC sampler, called the sequentially-allocated merge-split (SAMS) sampler. The sampler borrows ideas from sequential importance sampling. Splits are proposed by sequentially allocating observations to one of two split components using allocation probabilities that condition on previously allocated data. The SAMS sampler is applicable to general nonconjugate DPM models as well as conjugate models. Further, the proposed sampler is substantially more efficient than existing conjugate and nonconjugate samplers.

Modeling of extreme values in the presence of heterogeneity is still a relatively unexplored area. We consider losses pertaining to several related categories. For each category, we view exceedances over a given threshold as generated by a Poisson process whose intensity is regulated by a specific location, shape and scale parameter. Using a Bayesian approach, we develop a hierarchical mixture prior, with an unknown number of components, for each of the above parameters. Computations are performed using Reversible Jump MCMC. Our model accounts for possible grouping effects and takes advantage of the similarity across categories, both for estimation and prediction purposes. Some guidance on the specification of the prior distribution is provided, together with an assessment of inferential robustness. The method is illustrated throughout using a data set on large claims against a well-known insurance company over a 15-year period.

Nested sampling is a novel simulation method for approximating marginal likelihoods, proposed by Skilling (2007a,b). We establish that nested sampling leads to an error that vanishes at the standard Monte Carlo rate N −1/2, where N is a tuning parameter that is proportional to the computational effort, and that this error is asymptotically Gaussian. We show that the corresponding asymptotic variance typically grows linearly with the dimension of the parameter. We use these results to discuss the applicability and efficiency of nested sampling in realistic problems, including posterior distributions for mixtures. We propose an extension of nested sampling that makes it possible to avoid resorting to MCMC to obtain the simulated points. We study two alternative methods for computing marginal likelihood, which, in contrast with nested sampling, are based on draws from the posterior distribution and we conduct a comparison with nested sampling on several realistic examples.

Abstract: An important aspect of mixture modeling is the selection of the number of mixture components. In this paper, we discuss the Bayes factor as a selection tool. The discussion will focus on two aspects: computation of the Bayes factor and prior sensitivity. For the computation, we propose a variant of Chib’s estimator that accounts for the non-identifiability of the mixture components. To reduce the prior sensitivity of the Bayes factor, we propose to extend the model with a hyperprior. We further discuss the use of posterior predictive checks for examining the fit of the model. The ideas are illustrated by means of a psychiatric diagnosis example.

One of the main shortcomings of Markov chain Monte Carlo samplers is their inability to mix between modes of the target distribution. In this paper we show that advance knowledge of the location of these modes can be incorporated into the MCMC sampler by introducing mode-hopping moves that satisfy detailed balance. The proposed sampling algorithm explores local mode structure through local MCMC moves (e.g. diffusion or Hybrid Monte Carlo) but in addition also represents the relative strengths of the different modes correctly using a set of global moves. This ‘mode-hopping ’ MCMC sampler can be viewed as a generalization of the darting method [1]. We illustrate the method on a ‘real world ’ vision application of inferring 3-D human body pose from single 2-D images. 1