arXiv subjects

Bernard H. Fleury

Publications and source records attributed to Bernard H. Fleury.

11 recordsLinked to original sources

arXiv2025

Fast Variational Block-Sparse Bayesian Learning

We propose a variational Bayesian (VB) implementation of block-sparse Bayesian learning (BSBL) to compute proxy probability density functions (PDFs) that approximate the posterior PDFs of the weights and associated hyperparameters in a block-sparse linear model, resulting in an iterative algorithm coined variational BSBL (VA-BSBL). The priors of the hyperparameters are selected to belong to the family of generalized inverse Gaussian distributions. This family contains as special cases commonly used hyperpriors. Inspired by previous work on classical sparse Bayesian learning (SBL), we investigate the update stage in which the proxy PDFs of a single block of weights and of its associated hyperparameter are successively updated, while keeping the proxy PDFs of the other parameters fixed. This stage defines a nonlinear first-order recurrence relation for the mean of the proxy PDF of the hyperparameter. By iterating this relation "ad infinitum" we obtain a criterion that determines whether the so-generated sequence of hyperparameter means converges or diverges. Incorporating this criterion into the VA-BSBL algorithm yields a fast implementation, coined fast-BSBL (F-BSBL), which achieves a two-order-of-magnitude runtime improvement. We further identify the range of the parameters of the generalized inverse Gaussian distribution which result in an inherent pruning procedure that switches off "weak" components in the model, which is necessary to obtain sparse results. Lastly, we show that expectation-maximization (EM)-based and VB-based implementations of BSBL are identical methods. Thus, we extend a well-known result from classical SBL to BSBL. Consequently, F-BSBL and BSBL using coordinate ascent to maximize the marginal likelihood coincide. These results provide a unified framework for interpreting existing BSBL methods.

eess.SP↗

arXiv2023

Super-Resolution Estimation of UWB Channels including the Diffuse Component -- An SBL-Inspired Approach

In this paper, we present an iterative algorithm that detects and estimates the specular components and estimates the diffuse component of single-input-multiple-output (SIMO) ultra-wide-band (UWB) multipath channels. Specifically, the algorithm super-resolves the specular components in the delay-angle-of-arrival domain and estimates the parameters of a parametric model of the delay-angle power spectrum characterizing the diffuse component. Channel noise is also estimated. In essence, the algorithm solves the problem of estimating spectral lines (the specular components) in colored noise (generated by the diffuse component and channel noise). Its design is inspired by the sparse Bayesian learning (SBL) framework. As a result the iteration process contains a threshold condition that determines whether a candidate specular component shall be retained or pruned. By relying to results from extreme-value analysis the threshold of this condition is suitably adapted to ensure a prescribed probability of detecting spurious specular components. Studies using synthetic and real channel measurement data demonstrate the virtues of the algorithm: it is able to still detect and accurately estimate specular components, even when their separation in delay and angle is down to half the Rayleigh resolution limit (RRL) of the equipment; it is robust in the sense that it tends to return no more specular components than the actual ones. Finally, the algorithm is shown to outperform a state-of-the-art super-resolution channel estimator.

eess.SP↗

arXiv2018

An Iterative Receiver for OFDM With Sparsity-Based Parametric Channel Estimation

In this work we design a receiver that iteratively passes soft information between the channel estimation and data decoding stages. The receiver incorporates sparsity-based parametric channel estimation. State-of-the-art sparsity-based iterative receivers simplify the channel estimation problem by restricting the multipath delays to a grid. Our receiver does not impose such a restriction. As a result it does not suffer from the leakage effect, which destroys sparsity. Communication at near capacity rates in high SNR requires a large modulation order. Due to the close proximity of modulation symbols in such systems, the grid-based approximation is of insufficient accuracy. We show numerically that a state-of-the-art iterative receiver with grid-based sparse channel estimation exhibits a bit-error-rate floor in the high SNR regime. On the contrary, our receiver performs very close to the perfect channel state information bound for all SNR values. We also demonstrate both theoretically and numerically that parametric channel estimation works well in dense channels, i.e., when the number of multipath components is large and each individual component cannot be resolved.

cs.IT↗

arXiv2018

Capacity Scaling in MIMO Systems with General Unitarily Invariant Random Matrices

We investigate the capacity scaling of MIMO systems with the system dimensions. To that end, we quantify how the mutual information varies when the number of antennas (at either the receiver or transmitter side) is altered. For a system comprising $R$ receive and $T$ transmit antennas with $R>T$, we find the following: By removing as many receive antennas as needed to obtain a square system (provided the channel matrices before and after the removal have full rank) the maximum resulting loss of mutual information over all signal-to-noise ratios (SNRs) depends only on $R$, $T$ and the matrix of left-singular vectors of the initial channel matrix, but not on its singular values. In particular, if the latter matrix is Haar distributed the ergodic rate loss is given by $\sum_{t=1}^{T}\sum_{r=T+1}^{R}\frac{1}{r-t}$ nats. Under the same assumption, if $T,R\to \infty$ with the ratio $ϕ\triangleq T/R$ fixed, the rate loss normalized by $R$ converges almost surely to $H(ϕ)$ bits with $H(\cdot)$ denoting the binary entropy function. We also quantify and study how the mutual information as a function of the system dimensions deviates from the traditionally assumed linear growth in the minimum of the system dimensions at high SNR.

cs.IT↗

arXiv2017

Dynamical Functional Theory for Compressed Sensing

We introduce a theoretical approach for designing generalizations of the approximate message passing (AMP) algorithm for compressed sensing which are valid for large observation matrices that are drawn from an invariant random matrix ensemble. By design, the fixed points of the algorithm obey the Thouless-Anderson-Palmer (TAP) equations corresponding to the ensemble. Using a dynamical functional approach we are able to derive an effective stochastic process for the marginal statistics of a single component of the dynamics. This allows us to design memory terms in the algorithm in such a way that the resulting fields become Gaussian random variables allowing for an explicit analysis. The asymptotic statistics of these fields are consistent with the replica ansatz of the compressed sensing problem.

cs.IT↗

arXiv2016

Self-Averaging Expectation Propagation

We investigate the problem of approximate Bayesian inference for a general class of observation models by means of the expectation propagation (EP) framework for large systems under some statistical assumptions. Our approach tries to overcome the numerical bottleneck of EP caused by the inversion of large matrices. Assuming that the measurement matrices are realizations of specific types of ensembles we use the concept of freeness from random matrix theory to show that the EP cavity variances exhibit an asymptotic self-averaging property. They can be pre-computed using specific generating functions, i.e. the R- and/or S-transforms in free probability, which do not require matrix inversions. Our approach extends the framework of (generalized) approximate message passing -- assumes zero-mean iid entries of the measurement matrix -- to a general class of random matrix ensembles. The generalization is via a simple formulation of the R- and/or S-transforms of the limiting eigenvalue distribution of the Gramian of the measurement matrix. We demonstrate the performance of our approach on a signal recovery problem of nonlinear compressed sensing and compare it with that of EP.

cs.IT↗

arXiv2016

Cooperative Localization for Mobile Networks: A Distributed Belief Propagation - Mean Field Message Passing Algorithm

We propose a hybrid message passing method for distributed cooperative localization and tracking of mobile agents. Belief propagation and mean field message passing are employed for, respectively, the motion-related and measurement-related part of the factor graph. Using a Gaussian belief approximation, only three real values per message passing iteration have to be broadcast to neighboring agents. Despite these very low communication requirements, the estimation accuracy can be comparable to that of particle-based belief propagation.

eess.SY↗

arXiv2015

S-AMP for Non-linear Observation Models

Recently we extended Approximate message passing (AMP) algorithm to be able to handle general invariant matrix ensembles. In this contribution we extend our S-AMP approach to non-linear observation models. We obtain generalized AMP (GAMP) algorithm as the special case when the measurement matrix has zero-mean iid Gaussian entries. Our derivation is based upon 1) deriving expectation propagation (EP) like algorithms from the stationary-points equations of the Gibbs free energy under first- and second-moment constraints and 2) applying additive free convolution in free probability theory to get low-complexity updates for the second moment quantities.

cs.IT↗

arXiv2014

S-AMP: Approximate Message Passing for General Matrix Ensembles

In this work we propose a novel iterative estimation algorithm for linear observation systems called S-AMP whose fixed points are the stationary points of the exact Gibbs free energy under a set of (first- and second-) moment consistency constraints in the large system limit. S-AMP extends the approximate message-passing (AMP) algorithm to general matrix ensembles. The generalization is based on the S-transform (in free probability) of the spectrum of the measurement matrix. Furthermore, we show that the optimality of S-AMP follows directly from its design rather than from solving a separate optimization problem as done for AMP.

cs.IT↗

arXiv2011

Modeling of Reverberant Radio Channels Using Propagation Graphs

In measurements of in-room radio channel responses an avalanche effect can be observed: earliest signal components, which appear well separated in delay, are followed by an avalanche of components arriving with increasing rate of occurrence, gradually merging into a diffuse tail with exponentially decaying power. We model the channel as a propagation graph in which vertices represent transmitters, receivers, and scatterers, while edges represent propagation conditions between vertices. The recursive structure of the graph accounts for the exponential power decay and the avalanche effect. We derive a closed form expression for the graph's transfer matrix. This expression is valid for any number of interactions and is straightforward to use in numerical simulations. We discuss an example where time dispersion occurs only due to propagation in between vertices. Numerical experiments reveal that the graph's recursive structure yields both an exponential power decay and an avalanche effect.

math-ph↗

arXiv2011

Receiver Architectures for MIMO-OFDM Based on a Combined VMP-SP Algorithm

Iterative information processing, either based on heuristics or analytical frameworks, has been shown to be a very powerful tool for the design of efficient, yet feasible, wireless receiver architectures. Within this context, algorithms performing message-passing on a probabilistic graph, such as the sum-product (SP) and variational message passing (VMP) algorithms, have become increasingly popular. In this contribution, we apply a combined VMP-SP message-passing technique to the design of receivers for MIMO-ODFM systems. The message-passing equations of the combined scheme can be obtained from the equations of the stationary points of a constrained region-based free energy approximation. When applied to a MIMO-OFDM probabilistic model, we obtain a generic receiver architecture performing iterative channel weight and noise precision estimation, equalization and data decoding. We show that this generic scheme can be particularized to a variety of different receiver structures, ranging from high-performance iterative structures to low complexity receivers. This allows for a flexible design of the signal processing specially tailored for the requirements of each specific application. The numerical assessment of our solutions, based on Monte Carlo simulations, corroborates the high performance of the proposed algorithms and their superiority to heuristic approaches.

stat.ML↗