Representational Upper Bounds of Bayesian Networks
نویسندگان
چکیده
One of the fundamental issues of Bayesian networks is their representational power, re-ecting what kind of functions they can or cannot represent. In this paper, we rst prove an upper bound on the representational power of Augmented Naive Bayes. We then extend the result to general Bayesian networks. Roughly speaking, if a function contains an m-XOR, there exists no Bayesian networks with node having at most m ? 1 parents to represent it.
منابع مشابه
The Representational Power of Discrete Bayesian Networks
One of the most important fundamental properties of Bayesian networks is the representational power, re ecting what kind of functions they can or cannot represent. In this paper, we establish an association between the structural complexity of Bayesian networks and their representational power. We use the maximum number of nodes' parents as the measure for the Bayesian network structural comple...
متن کاملA Survey on Stability Measure of Networks
In this paper we discuss about tenacity and its properties in stability calculation. We indicate relationships between tenacity and connectivity, tenacity and binding number, tenacity and toughness. We also give good lower and upper bounds for tenacity.
متن کاملInference in Multilayer Networks via Large Deviation Bounds
VIa We study probabilistic inference in large, layered Bayesian networks represented as directed acyclic graphs. We show that the intractability of exact inference in such networks does not preclude their effective use. We give algorithms for approximate probabilistic inference that exploit averaging phenomena occurring at nodes with large numbers of parents . We show that these algorithms comp...
متن کاملImproving Bound Propagation
This paper extends previously proposed bound propagation algorithm [11] for computing lower and upper bounds on posterior marginals in Bayesian networks. We improve the bound propagation scheme by taking advantage of the directionality in Bayesian networks and applying the notion of relevant subnetwork. We also propose an approximation scheme for the linear optimization subproblems. We demonstr...
متن کاملInner Product Spaces for Bayesian Networks
Bayesian networks have become one of the major models used for statistical inference. We study the question whether the decisions computed by a Bayesian network can be represented within a low-dimensional inner product space. We focus on two-label classification tasks over the Boolean domain. As main results we establish upper and lower bounds on the dimension of the inner product space for Bay...
متن کامل