Message-passing algorithms consist of a parallelised computing scheme to estimate the marginals of a high-dimensional probability distribution. They have been used in various areas where the statistics of a large number of interacting variables have to be studied, including statistical physics, artificial intelligence, decoding in information theory. This thesis desctibes the algebraic and topological structures in which message-passing algorithms naturally take place. In most applications, the probability distribution p is defined by a Markov field or graphical model, i.e. as a product of local factors depending only on small subsets of interacting variables. Equivalently, the total energy H = - ln p (or log-likelihood) is a sum of local ...
International audienceA number of problems in statistical physics and computer science can be expres...
Belief propagation over pairwise connected Markov Random Fields has become a widely used approach, a...
Algorithms on graphs are used extensively in many applications and research areas. Such applications...
Les algorithmes à propagation de messages constituent un schéma de calcul parallèle pour estimer les...
This thesis addresses the problem of inference in factor graphs, especially the LDPC codes, almost s...
Belief propagation (BP) was only supposed to work for tree-like networks but works surprisingly well...
An important part of problems in statistical physics and computer science can be expressed as the co...
In this work, we focus on the design and estimation - from partial observations - of graphical model...
Abstract—Inference problems in graphical models can be rep-resented as a constrained optimization of...
We often encounter probability distributions given as unnormalized products of non-negative function...
A large number of optimization, inverse, combinatorial and out-of-equilibrium problems, arising in t...
The research reported in this thesis focuses on approximation techniques for inference in graphical ...
Systems and control theory have found wide application in the analysis and design of numerical algor...
In the last years several problems been studied at the interface between statistical physics and com...
We rigorously establish a close relationship between message passing algorithms and models of neurod...
International audienceA number of problems in statistical physics and computer science can be expres...
Belief propagation over pairwise connected Markov Random Fields has become a widely used approach, a...
Algorithms on graphs are used extensively in many applications and research areas. Such applications...
Les algorithmes à propagation de messages constituent un schéma de calcul parallèle pour estimer les...
This thesis addresses the problem of inference in factor graphs, especially the LDPC codes, almost s...
Belief propagation (BP) was only supposed to work for tree-like networks but works surprisingly well...
An important part of problems in statistical physics and computer science can be expressed as the co...
In this work, we focus on the design and estimation - from partial observations - of graphical model...
Abstract—Inference problems in graphical models can be rep-resented as a constrained optimization of...
We often encounter probability distributions given as unnormalized products of non-negative function...
A large number of optimization, inverse, combinatorial and out-of-equilibrium problems, arising in t...
The research reported in this thesis focuses on approximation techniques for inference in graphical ...
Systems and control theory have found wide application in the analysis and design of numerical algor...
In the last years several problems been studied at the interface between statistical physics and com...
We rigorously establish a close relationship between message passing algorithms and models of neurod...
International audienceA number of problems in statistical physics and computer science can be expres...
Belief propagation over pairwise connected Markov Random Fields has become a widely used approach, a...
Algorithms on graphs are used extensively in many applications and research areas. Such applications...