Expectation-Maximization Gaussian-Mixture Approximate Message Passing
Jeremy Vila,Philip Schniter +1 more
Reads0
Chats0
TLDR
An empirical-Bayesian technique is proposed that simultaneously learns the signal distribution while MMSE-recovering the signal-according to the learned distribution-using AMP, and model the non-zero distribution as a Gaussian mixture, and learn its parameters through expectation maximization, using AMP to implement the expectation step.Abstract:
When recovering a sparse signal from noisy compressive linear measurements, the distribution of the signal's non-zero coefficients can have a profound effect on recovery mean-squared error (MSE). If this distribution was a priori known, then one could use computationally efficient approximate message passing (AMP) techniques for nearly minimum MSE (MMSE) recovery. In practice, however, the distribution is unknown, motivating the use of robust algorithms like LASSO-which is nearly minimax optimal-at the cost of significantly larger MSE for non-least-favorable distributions. As an alternative, we propose an empirical-Bayesian technique that simultaneously learns the signal distribution while MMSE-recovering the signal-according to the learned distribution-using AMP. In particular, we model the non-zero distribution as a Gaussian mixture and learn its parameters through expectation maximization, using AMP to implement the expectation step. Numerical experiments on a wide range of signal classes confirm the state-of-the-art performance of our approach, in both reconstruction error and runtime, in the high-dimensional regime, for most (but not all) sensing operators.read more
Citations
More filters
Proceedings ArticleDOI
Correlation learning on joint support recovery for more sources than measurements
Sung-En Chiu,Bhaskar D. Rao +1 more
TL;DR: This work first analyzes the MSBL algorithm by Wipf and Rao, and provides its limit in the M ≤ D regime, and further develops Bayesian methods for learning the correlation structures both temporally or spatially.
Dissertation
Algorithms for 3D time-of-flight imaging
TL;DR: This thesis describes the design and implementation of two novel frameworks and processing schemes for 3D imaging based on time-of-flight (TOF) principles that incorporate both accurate probabilistic modeling for the measurement process and underlying scene depth map sparsity to accurately extend the unambiguous depth range of the camera.
Proceedings ArticleDOI
YAMPA: Yet Another Matching Pursuit Algorithm for compressive sensing
TL;DR: This paper formulates an iterative algorithm, termed yet another matching pursuit algorithm (YAMPA), for recovery of sparse signals from compressive measurements, and shows that YAMPA uniformly outperforms other pursuit algorithms for the case of thresholding parameters chosen in a clairvoyant fashion.
Journal ArticleDOI
Joint Activity and Channel Estimation for Extra-Large MIMO Systems
TL;DR: In this article , a bilinear Bayesian inference algorithm was proposed to jointly estimate the associated channel coefficients, user activity patterns, and sub-array activity patterns in XL-MIMO systems.
Journal ArticleDOI
Influence of multi-walled carbon nanotubes on the fracture response and phase distribution of metakaolin-based potassium geopolymers
Jiaxin Chen,Ange-Therese Akono +1 more
TL;DR: In this paper, the effects of multi-walled carbon nanotubes (MWCNTs) on the chemistry, microstructure, phase distribution, and fracture response of potassium-based metakaolin geopolymers at the microscopic scale were investigated.
References
More filters
Journal ArticleDOI
Maximum likelihood from incomplete data via the EM algorithm
Journal ArticleDOI
Regression Shrinkage and Selection via the Lasso
TL;DR: A new method for estimation in linear models called the lasso, which minimizes the residual sum of squares subject to the sum of the absolute value of the coefficients being less than a constant, is proposed.
Journal ArticleDOI
A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
Amir Beck,Marc Teboulle +1 more
TL;DR: A new fast iterative shrinkage-thresholding algorithm (FISTA) which preserves the computational simplicity of ISTA but with a global rate of convergence which is proven to be significantly better, both theoretically and practically.
Journal ArticleDOI
Atomic Decomposition by Basis Pursuit
TL;DR: Basis Pursuit (BP) is a principle for decomposing a signal into an "optimal" superposition of dictionary elements, where optimal means having the smallest l1 norm of coefficients among all such decompositions.
Journal ArticleDOI
Sparse bayesian learning and the relevance vector machine
TL;DR: It is demonstrated that by exploiting a probabilistic Bayesian learning framework, the 'relevance vector machine' (RVM) can derive accurate prediction models which typically utilise dramatically fewer basis functions than a comparable SVM while offering a number of additional advantages.