Latent binary MRF for online reconstruction of large scale systems

DOI10.1007/S10472-015-9470-XMaRDI QIDQ505979zbMATH OpenOpenAlexFDO

Authors Victorin Martin, Jean-Marc Lasgouttes, Cyril Furtlehner

Publication date 27 January 2017

Published in Annals of Mathematics and Artificial Intelligence (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1312.6607

zbMATH Keywords

latent variablesinferenceMarkov random fieldbelief propagationsoft constraints

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Random fields (60G60) Interacting random processes; statistical mechanics type models; percolation theory (60K35)

Abstract: We propose a probabilistic graphical model realizing a minimal encoding of real variables dependencies based on possibly incomplete observation and an empirical cumulative distribution function per variable. The target application is a large scale partially observed system, like e.g. a traffic network, where a small proportion of real valued variables are observed, and the other variables have to be predicted. Our design objective is therefore to have good scalability in a real-time setting. Instead of attempting to encode the dependencies of the system directly in the description space, we propose a way to encode them in a latent space of binary variables, reflecting a rough perception of the observable (congested/non-congested for a traffic road). The method relies in part on message passing algorithms, i.e. belief propagation, but the core of the work concerns the definition of meaningful latent variables associated to the variables of interest and their pairwise dependencies. Numerical experiments demonstrate the applicability of the method in practice.

Recommendations

• An Ising model for road traffic inference
• Network tomography for integer-valued traffic
• Pairwise MRF models selection for traffic inference
• Propagation of information on undirected dependency graphs for road traffic inference
• Traffic data reconstruction based on Markov random field modeling

Cites work

• scientific article; zbMATH DE number 1666084 (Why is no real title available?)
• scientific article; zbMATH DE number 5818610 (Why is no real title available?)
• scientific article; zbMATH DE number 48812 (Why is no real title available?)
• scientific article; zbMATH DE number 3567782 (Why is no real title available?)
• scientific article; zbMATH DE number 1273988 (Why is no real title available?)
• Adaptive cluster expansion for the inverse Ising problem: convergence, algorithm and tests
• Approximate Learning Algorithm in Boltzmann Machines
• Approximate inference in Boltzmann machines
• Approximate inverse Ising models close to a Bethe reference point
• Constructing Free-Energy Approximations and Generalized Belief Propagation Algorithms
• Estimating the ``wrong graphical model: benefits in the computation-limited setting
• Factor graphs and the sum-product algorithm
• Generalized Iterative Scaling for Log-Linear Models
• High-dimensional Ising model selection using \(\ell _{1}\)-regularized logistic regression
• Loopy belief propagation: convergence and effects of message errors
• Nearest neighbor pattern classification
• On the revision of probabilistic beliefs using uncertain evidence
• Prior Probabilities
• Probability Theory
• Sparse inverse covariance estimation with the graphical lasso
• Sufficient Conditions for Convergence of the Sum–Product Algorithm
• The PUMAS library

Cited in

(5)

• Pairwise MRF models selection for traffic inference
• An Ising model for road traffic inference
• Cycle-based cluster variational method for direct and inverse inference
• Propagation of information on undirected dependency graphs for road traffic inference
• Traffic data reconstruction based on Markov random field modeling

Describes a project that uses

Uses Software

• glasso

This page was built for publication: Latent binary MRF for online reconstruction of large scale systems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q505979)