Forward recursions and normalizing constant for Gibbs fields
نویسنده
چکیده
Maximum likelihood parameter estimation is frequently replaced by various techniques because of its intractable normalizing constant. In the same way, the literature displays various alternatives for distributions involving such unreachable constants. In this paper, we consider a Gibbs distribution π and present a recurrence formula allowing a recursive calculus of the marginals of π and in the same time its normalizing constant. The numerical performance of this algorithm is evaluated for several examples, particularly for an Ising model on a lattice.
منابع مشابه
Calibration of conditional composite likelihood for Bayesian inference on Gibbs random fields
Gibbs random fields play an important role in statistics, however, the resulting likelihood is typically unavailable due to an intractable normalizing constant. Composite likelihoods offer a principled means to construct useful approximations. This paper provides a mean to calibrate the posterior distribution resulting from using a composite likelihood and illustrate its performance in several ...
متن کاملExact marginals and normalizing constant for Gibbs distributions
We present a recursive algorithm for the calculation of the marginal of a Gibbs distribution π. A direct consequence is the calculation of the normalizing constant of π. Résumé Récurrences et constante de normalisation pour des modèles de Gibbs. Nous proposons dans ce travail une récurrence sur les lois marginales d’une distribution de Gibbs π. Une conséquence directe est le calcul exact de la ...
متن کاملLearning Stochastic Path Planning Models from Video Images
We describe a probabilistic framework for learning models of pedestrian trajectories in general outdoor scenes. Possible applications include simulation of motion in computer graphics, video surveillance, and architectural design and analysis. The models are based on a combination of Kalman filters and stochastic path-planning via landmarks, where the landmarks are learned from the data. A dyna...
متن کاملAdaptive ABC model choice and geometric summary statistics for hidden Gibbs random fields
Selecting between different dependency structures of hidden Markov random field can be very challenging, due to the intractable normalizing constant in the likelihood. We answer this question with approximate Bayesian computation (ABC) which provides a model choice method in the Bayesian paradigm. This comes after the work of Grelaud et al. (2009) who exhibited sufficient statistics on directly...
متن کاملExact and approximate recursive calculations for binary Markov random fields defined on graphs
In this paper we propose computationally feasible approximations to binary Markov random fields. The basis of the approximation is the forward-backward algorithm. This exact algorithm is computationally feasible only for fields defined on small lattices. The forward part of the algorithm computes a series of joint marginal distributions by summing out each variable in turn. We represent these j...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2009