#### Filter Results:

#### Publication Year

2001

2016

#### Publication Type

#### Co-author

#### Publication Venue

#### Key Phrases

Learn More

We present algorithms for the generation of uniformly distributed Bayesian networks with constraints on induced width. The algorithms use ergodic Markov chains to generate samples. The introduction of constraints on induced width leads to realistic networks but requires new techniques. A tool that generates random networks is presented and applications are… (More)

This paper presents new methods for generation of random Bayesian networks. Such methods can be used to test inference and learning algorithms for Bayesian networks, and to obtain insights on average properties of such networks. Any method that generates Bayesian networks must first generate directed acyclic graphs (the " structure " of the network) and… (More)

This paper presents two approximate algorithms for inference in graphi-cal models for binary random variables and imprecise probability. Exact inference in such models is extremely challenging in multiply-connected graphs. We describe and implement two new approximate algorithms. The first one is the Iterated Partial Evaluation (IPE) algorithm, directly… (More)

This paper investigates a representation language with flexibility inspired by probabilistic logic and compactness inspired by relational Bayesian networks. The goal is to handle propositional and first-order constructs together with precise, imprecise , indeterminate and qualitative probabilis-tic assessments. The paper shows how this can be achieved… (More)

An important aspect of probabilistic inference in embedded real-time systems is flexibility to handle changes and limitations in space and time resources. We present algorithms for probabilistic inference that focus on simultaneous adaptation with respect to these resources. We discuss techniques to reduce memory consumption in Bayesian network inference,… (More)

Credal networks generalize Bayesian networks relaxing numerical parameters. This considerably expands expressivity, but makes belief updating a hard task even on polytrees. Nevertheless, if all the variables are binary, polytree-shaped credal networks can be efficiently updated by the 2U algorithm. In this paper we present a binarization algorithm, that… (More)

We present algorithms for the generation of uniformly distributed Bayesian networks with constraints on induced width. The algorithms use ergodic Markov chains to generate samples , building upon previous algorithms by the authors. The introduction of constraints on induced width leads to more realistic results but requires new techniques. We discuss three… (More)

Graph-theoretical representations for sets of probability measures (credal networks) generally display high complexity, and approximate inference seems to be a natural solution for large networks. This paper introduces a variational approach to approximate inference in credal networks: we show how to formulate mean field approximations using naive (fully… (More)

In this work we show how to generate random Bayesian networks and how to test inference algorithms using these samples. First, we present a new method to generate random networks through Markov chains. We then use random networks to investigate the performance of quasi-random numbers in Gibbs sampling algorithms for inference. We present experimental… (More)