Showing 1 to 10 of 1388 matching Articles
Results per page:
Export (CSV)
By
Everitt, Richard G.; Johansen, Adam M.; Rowing, Ellen; EvdemonHogan, Melina
Show all (4)
10 Citations
Models for which the likelihood function can be evaluated only up to a parameterdependent unknown normalizing constant, such as Markov random field models, are used widely in computer science, statistical physics, spatial statistics, and network analysis. However, Bayesian analysis of these models using standard Monte Carlo methods is not possible due to the intractability of their likelihood functions. Several methods that permit exact, or close to exact, simulation from the posterior distribution have recently been developed. However, estimating the evidence and Bayes’ factors for these models remains challenging in general. This paper describes new random weight importance sampling and sequential Monte Carlo methods for estimating BFs that use simulation to circumvent the evaluation of the intractable likelihood, and compares them to existing methods. In some cases we observe an advantage in the use of biased weight estimates. An initial investigation into the theoretical and empirical properties of this class of methods is presented. Some support for the use of biased estimates is presented, but we advocate caution in the use of such estimates.
more …
By
Jagadeeswaran, R.; Hickernell, Fred J.
1 Citations
Automatic cubatures approximate integrals to userspecified error tolerances. For highdimensional problems, it is difficult to adaptively change the sampling pattern, but one can automatically determine the sample size, n, given a reasonable, fixed sampling pattern. We take this approach here using a Bayesian perspective. We postulate that the integrand is an instance of a Gaussian stochastic process parameterized by a constant mean and a covariance kernel defined by a scale parameter times a parameterized function specifying how the integrand values at two different points in the domain are related. These hyperparameters are inferred or integrated out using integrand values via one of three techniques: empirical Bayes, full Bayes, or generalized crossvalidation. The sample size, n, is increased until the halfwidth of the credible interval for the Bayesian posterior mean is no greater than the error tolerance. The process outlined above typically requires a computational cost of
$$O(N_{\text {opt}}n^3)$$
, where
$$N_{\text {opt}}$$
is the number of optimization steps required to identify the hyperparameters. Our innovation is to pair low discrepancy nodes with matching covariance kernels to lower the computational cost to
$$O(N_{\text {opt}} n \log n)$$
. This approach is demonstrated explicitly with rank1 lattice sequences and shiftinvariant kernels. Our algorithm is implemented in the Guaranteed Automatic Integration Library (GAIL).
more …
By
Vaisman, Radislav; Botev, Zdravko I.; Ridder, Ad
2 Citations
In this paper we describe a sequential importance sampling (SIS) procedure for counting the number of vertex covers in general graphs. The optimal SIS proposal distribution is the uniform over a suitably restricted set, but is not implementable. We will consider two proposal distributions as approximations to the optimal. Both proposals are based on randomization techniques. The first randomization is the classic probability model of random graphs, and in fact, the resulting SIS algorithm shows polynomial complexity for random graphs. The second randomization introduces a probabilistic relaxation technique that uses Dynamic Programming. The numerical experiments show that the resulting SIS algorithm enjoys excellent practical performance in comparison with existing methods. In particular the method is compared with cachet—an exact model counter, and the state of the art SampleSearch, which is based on Belief Networks and importance sampling.
more …
By
Richardson, Robert ; Kottas, Athanasios; Sansó, Bruno
1 Citations
Integrodifference equations (IDEs) provide a flexible framework for dynamic modeling of spatiotemporal data. The choice of kernel in an IDE model relates directly to the underlying physical process modeled, and it can affect model fit and predictive accuracy. We introduce Bayesian nonparametric methods to the IDE literature as a means to allow flexibility in modeling the kernel. We propose a mixture of normal distributions for the IDE kernel, built from a spatial Dirichlet process for the mixing distribution, which can model kernels with shapes that change with location. This allows the IDE model to capture nonstationarity with respect to location and to reflect a changing physical process across the domain. We address computational concerns for inference that leverage the use of Hermite polynomials as a basis for the representation of the process and the IDE kernel, and incorporate Hamiltonian Markov chain Monte Carlo steps in the posterior simulation method. An example with synthetic data demonstrates that the model can successfully capture locationdependent dynamics. Moreover, using a data set of ozone pressure, we show that the spatial Dirichlet process mixture model outperforms several alternative models for the IDE kernel, including the state of the art in the IDE literature, that is, a Gaussian kernel with locationdependent parameters.
more …
By
Aston, J. A. D.; Peng, J. Y.; Martin, D. E. K.
6 Citations
A method for efficiently calculating exact marginal, conditional and joint distributions for change points defined by general finite state Hidden Markov Models is proposed. The distributions are not subject to any approximation or sampling error once parameters of the model have been estimated. It is shown that, in contrast to sampling methods, very little computation is needed. The method provides probabilities associated with change points within an interval, as well as at specific points.
more …
By
Meilă, Marina; Jaakkola, Tommi
21 Citations
In this paper we present decomposable priors, a family of priors over structure and parameters of tree belief nets for which Bayesian learning with complete observations is tractable, in the sense that the posterior is also decomposable and can be completely determined analytically in polynomial time. Our result is the first where computing the normalization constant and averaging over a superexponential number of graph structures can be performed in polynomial time. This follows from two main results: First, we show that factored distributions over spanning trees in a graph can be integrated in closed form. Second, we examine priors over tree parameters and show that a set of assumptions similar to Heckerman, Geiger and Chickering (1995) constrain the tree parameter priors to be a compactly parametrized product of Dirichlet distributions. Besides allowing for exact Bayesian learning, these results permit us to formulate a new class of tractable latent variable models in which the likelihood of a data point is computed through an ensemble average over tree structures.
more …
By
McDermott, James P.; Babu, G. Jogesh; Liechty, John C.; Lin, Dennis K. J.
Show all (4)
6 Citations
We consider the problem of density estimation when the data is in the form of a continuous stream with no fixed length. In this setting, implementations of the usual methods of density estimation such as kernel density estimation are problematic. We propose a method of density estimation for massive datasets that is based upon taking the derivative of a smooth curve that has been fit through a set of quantile estimates. To achieve this, a lowstorage, singlepass, sequential method is proposed for simultaneous estimation of multiple quantiles for massive datasets that form the basis of this method of density estimation. For comparison, we also consider a sequential kernel density estimator. The proposed methods are shown through simulation study to perform well and to have several distinct advantages over existing methods.
more …
By
Pewsey, Arthur; Kato, Shogo
1 Citations
The Wehrly–Johnson family of bivariate circular distributions is by far the most general one currently available for modelling data on the torus. It allows complete freedom in the specification of the marginal circular densities as well as the binding circular density which regulates any dependence that might exist between them. We propose a parametric bootstrap approach for testing the goodnessoffit of Wehrly–Johnson distributions when the forms of their marginal and binding densities are assumed known. The approach admits the use of any test for toroidal uniformity, and we consider versions of it incorporating three such tests. Simulation is used to illustrate the operating characteristics of the approach when the underlying distribution is assumed to be bivariate wrapped Cauchy. An analysis of wind direction data recorded at a Texan weather station illustrates the use of the proposed goodnessoffit testing procedure.
more …
By
Longford, Nicholas T.
8 Citations
The weaknesses of established model selection procedures based on hypothesis testing and similar criteria are discussed and an alternative based on synthetic (composite) estimation is proposed. It is developed for the problem of prediction in ordinary regression and its properties are explored by simulations for the simple regression. Extensions to a general setting are described and an example with multiple regression is analysed. Arguments are presented against using a selected model for any inferences.
more …
By
Heaton, T. J.
1 Citations
This paper addresses, via thresholding, the estimation of a possibly sparse signal observed subject to Gaussian noise. Conceptually, the optimal threshold for such problems depends upon the strength of the underlying signal. We propose two new methods that aim to adapt to potential local variation in this signal strength and select a variable threshold accordingly. Our methods are based upon an empirical Bayes approach with a smoothly variable mixing weight chosen via either spline or kernel based marginal maximum likelihood regression. We demonstrate the excellent performance of our methods in both one and twodimensional estimation when compared to various alternative techniques. In addition, we consider the application to wavelet denoising where reconstruction quality is significantly improved with local adaptivity.
more …
