We show how to find a minimum loop cutset in a Bayesian network with high probability. Finding such a loop cutset is the first step in Pearl's method of conditioning for inference. Our random algorithm for finding a loop cutset, called RepeatedWGuessI, outputs a minimum loop cutset, after O(c \Delta 6 k kn) steps, with probability at least 1 \Gamma (1 \Gamma 1 6 k ) c6 k , where c ? 1 is a constant specified by the user, k is the size of a minimum weight loop cutset, and n is the number of vertices. We also show empirically that a variant of this algorithm, called WRA, often finds a loop cutset that is closer to the minimum loop cutset than the ones found by the best deterministic algorithms known. 1

Abstract not found

In this paper we propose a new approach to probabilistic inference on belief networks, global conditioning, which is a simple generalization of Pearl's (1986b) method of loopcutset conditioning. We show that global conditioning, as well as loop-cutset conditioning, can be thought of as a special case of the method of Lauritzen and Spiegelhalter (1988) as refined by Jensen et al (1990a; 1990b).

Abstract—A method is presented to segment multidimensional images using a multiscale (hyperstack) approach with probabilistic linking. A hyperstack is a voxel-based multiscale data structure whose levels are constructed by convolving the original image with a Gaussian kernel of increasing width. Between voxels at adjacent scale levels, child-parent linkages are established according to a model-directed linkage scheme. In the resulting tree-like data structure, roots are formed to indicate the most plausible locations in scale space where segments in the original image are represented by a single voxel. The final segmentation is obtained by tracing back the linkages for all roots. The present paper deals with probabilistic (or multiparent) linking, i.e., a set-up in which a child voxel can be linked to more than one parent voxel. The multiparent linkage structure is translated into a list of probabilities that are indicative of which voxels are partial volume voxels and to which extent. Probability maps are generated to visualize the progress of weak linkages in scale space when going from fine to coarser scale. This is shown to be a valuable tool for the detection of voxels that are difficult to segment properly. The output of a probabilistic hyperstack can be directly related to the opacities used in volume renderers. Results are shown both for artificial and real world (medical) images. It is demonstrated that probabilistic linking gives a significantly improved segmentation as compared with conventional (single-parent) linking. The improvement is quantitatively supported by an objective evaluation method. Index Terms—Image segmentation, multiscale analysis, scale space, probability maps, partial volume artifact, object definition. 1

Local conditioning (LC) is an exact algorithm for computing probability in Bayesian networks, developed as an extension of Kim and Pearl's algorithm for singly-connected networks. A list of variables associated to each node guarantees that only the nodes inside a loop are conditioned on the variable which breaks it. The main advantage of this algorithm is that it computes the probability directly on the original network instead of building a cluster tree, and this can save time when debugging a model and when the sparsity of evidence allows a pruning of the network. The algorithm is also advantageous when some families in the network interact through AND/OR gates. A parallel implementation of the algorithm with a processor for each node is possible even in the case of multiply-connected networks. 1 Introduction A Bayesian network is an acyclic directed graph in which every node represents a random variable, together with a probability distribution such that P (x 1 ; : : : ; x n ) = ...

A feedback vertex set of an undirected graph is a subset of vertices that intersects with the vertex set of each cycle in the graph. Given an undirected graph G with n vertices and weights on its vertices, polynomial-time algorithms are provided for approximating the problem of finding a feedback vertex set of G with a smallest weight. When the weights of all vertices in G are equal, the performance ratio attained by these algorithms is 4 \Gamma (2=n). This improves a previous algorithm which achieved an approximation factor of O( p log n) for this case. For general vertex weights, the performance ratio becomes minf2\Delta 2 ; 4 log 2 ng where \Delta denotes the maximum degree in G. For the special case of planar graphs this ratio is reduced to 10. An interesting special case of weighted graphs where a performance ratio of 4 \Gamma (2=n) is achieved is the one where a prescribed subset of the vertices, so called blackout vertices, is not allowed to participate in any feedback verte...

Bayesian belief networks or causal probabilistic networks may reach a certain size and complexity where the computations involved in exact probabilistic inference on the network tend to become rather time consuming. Methods for approximating a network by a simpler one allow the computational complexity of probabilistic inference on the network to be reduced at least to some extend. We propose a general framework for approximating Bayesian belief networks based on model simplification by arc removal. The approximation method aims at reducing the computational complexity of probabilistic inference on a network at the cost of introducing a bounded error in the prior and posterior probabilities inferred. We present a practical approximation scheme and give some preliminary results. 1 Introduction Today, more and more applications based on the Bayesian belief network 1 formalism are emerging for reasoning and decision making in problem domains with inherent uncertainty. Current applicati...

We show how to find a small loop cutset in a Bayesian network.

Pedigree loops pose a difficult computational challenge in genetic linkage analysis. The most popular linkage analysis package, LINKAGE, uses an algorithm that converts a looped pedigree into a loopless pedigree, which is traversed many times. The conversion is controlled by user-selection of individuals to act as loop breakers. The selection of loop breakers has significant impact on the running time of the subsequent linkage analysis. We have automated the process of selecting loop breakers, implemented a hybrid algorithm for it in the FASTLINK version of LINKAGE, and tested it on many real pedigrees with excellent performance. We point out that there is no need to break each loop to FASTLINK, a single individual can serve as a loop breaker for many loops. Our algorithm for finding loop breakers, called LoopBreaker, is a combination of: (1) a new algorithm that is guaranteed to be optimal on the special case of pedigrees with no multiple marriages and (2) an adaptation of a known algorithm for breaking loops in general graphs. The contribution of this work is to adapt abstract methods from computer science to a challenging problem in genetics.

We present two algorithms for exact and approximate inference in causal networks. The first algorithm, dynamic conditioning, is a refinement of cutset conditioning that has linear complexity on some networks for which cutset conditioning is exponential. The second algorithm, B-conditioning, is an algorithm for approximate inference that allows one to trade-off the quality of approximations with the computation time. We also present some experimental results illustrating the properties of the proposed algorithms. 1 INTRODUCTION Cutset conditioning is one of the earliest algorithms for evaluating multiply connected networks [6]. Cutset conditioning works by reducing multiply connected networks into a number of conditioned singly connected networks, each corresponding to a particular instantiation of a loop cutset [6, 7]. Cutset conditioning is simple, but leads to an exponential number of conditioned networks. Therefore, cutset conditioning is not practical unless the size of a loop cut...