Fundamentals of statistical exponential families: with applications in statistical decision theory
Fundamentals of statistical exponential families: with applications in statistical decision theory
Probabilistic reasoning in intelligent systems: networks of plausible inference
Probabilistic reasoning in intelligent systems: networks of plausible inference
Dykstra's alternating projection algorithm for two sets
Journal of Approximation Theory
A family of algorithms for approximate bayesian inference
A family of algorithms for approximate bayesian inference
Stochastic reasoning, free energy, and information geometry
Neural Computation
Distributed iterative decoding and estimation via expectation propagation: performance and convergence
Iterative multiuser detection and error control code decoding in random CDMA
IEEE Transactions on Signal Processing
Cross-entropy and iterative decoding
IEEE Transactions on Information Theory
Good error-correcting codes based on very sparse matrices
IEEE Transactions on Information Theory
The geometry of turbo-decoding dynamics
IEEE Transactions on Information Theory
Factor graphs and the sum-product algorithm
IEEE Transactions on Information Theory
Codes on graphs: normal realizations
IEEE Transactions on Information Theory
The capacity of low-density parity-check codes under message-passing decoding
IEEE Transactions on Information Theory
Design of capacity-approaching irregular low-density parity-check codes
IEEE Transactions on Information Theory
Analyzing the turbo decoder using the Gaussian approximation
IEEE Transactions on Information Theory
Iterative multiuser joint decoding: unified framework and asymptotic analysis
IEEE Transactions on Information Theory
Information projections revisited
IEEE Transactions on Information Theory
Information geometry of turbo and low-density parity-check codes
IEEE Transactions on Information Theory
Constructing free-energy approximations and generalized belief propagation algorithms
IEEE Transactions on Information Theory
Nonlinear dynamics of iterative decoding systems: analysis and applications
IEEE Transactions on Information Theory
Turbo Decoding as Iterative Constrained Maximum-Likelihood Sequence Detection
IEEE Transactions on Information Theory
Turbo decoding as an instance of Pearl's “belief propagation” algorithm
IEEE Journal on Selected Areas in Communications
Iterative turbo decoder analysis based on density evolution
IEEE Journal on Selected Areas in Communications
Nonparametric belief propagation for self-localization of sensor networks
IEEE Journal on Selected Areas in Communications
A factor graph approach to link loss monitoring in wireless sensor networks
IEEE Journal on Selected Areas in Communications
| Hi-index | 754.84 |
Belief propagation is shown to be an instance of a hybrid between two projection algorithms in the convex programming literature: Dykstra's algorithm with cyclic Bregman projections and an alternating Bregman projections algorithm. Via this connection, new results concerning the convergence and performance of belief propagation can be proven by exploiting the corresponding literature about the two projections algorithms it hybridizes. In this regard, it is identified that the lack of guaranteed convergence for belief propagation results from the asymmetry of its Bregman divergence by proving that when the associated hybrid projection algorithm generalization is used with a symmetric Bregman divergence, it always converges. Additionally, by characterizing factorizations that are close to acyclic in a manner independent of their girth, a new collection of distributions for which belief propagation is guaranteed to perform well is identified using the new projection algorithm framework.