Bilinear Generalized Approximate Message Passing—Part II: Applications
Authors:
- 12 September 2014
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Signal Processing
- Vol. 62 (22) , 5854-5867
Abstract
In this paper, we extend the generalized approximate message passing (G-AMP) approach, originally proposed for high-dimensional generalized-linear regression in the context of compressive sensing, to the generalized-bilinear case. In Part I of this two-part paper, we derived our Bilinear G-AMP (BiG-AMP) algorithm as an approximation of the sum-product belief propagation algorithm in the high-dimensional limit, and proposed an adaptive damping mechanism that aids convergence under finite problem sizes, an expectation-maximization (EM)-based method to automatically tune the parameters of the assumed priors, and two rank-selection strategies. Here, in Part II, we discuss the specializations of BiG-AMP to the problems of matrix completion, robust PCA, and dictionary learning, and present the results of an extensive empirical study comparing BiG-AMP to state-of-the-art algorithms on each problem. Our numerical results, using both synthetic and real-world datasets, demonstrate that EM-BiG-AMP yields excellent reconstruction accuracy (often best in class) while maintaining competitive runtimes.Keywords
Funding Information
- AFOSR Lab Task (11RY02COR)
- NSF (IIP-0968910, CCF-1018368, CCF-1218754)
- DARPA/ONR (N66001-10-1-4090)
- European Commission (MIRG-268398)
- ERC Future Proof
- SNF (200021-132548)
- SNF (200021-146750)
- SNF (CRSII2-147633)
This publication has 19 references indexed in Scilit:
- Expectation-Maximization Gaussian-Mixture Approximate Message PassingIEEE Transactions on Signal Processing, 2013
- Phase diagram and approximate message passing for blind calibration and dictionary learning2013
- On $l_q$ Optimization and Matrix CompletionIEEE Transactions on Signal Processing, 2012
- Solving a low-rank factorization model for matrix completion by a nonlinear successive over-relaxation algorithmMathematical Programming Computation, 2012
- Sparse Bayesian Methods for Low-Rank Matrix EstimationIEEE Transactions on Signal Processing, 2012
- Online identification and tracking of subspaces from highly incomplete information2010
- Message passing algorithms for compressed sensing: I. motivation and construction2010
- Message-passing algorithms for compressed sensingProceedings of the National Academy of Sciences of the United States of America, 2009
- Non-linear matrix factorization with Gaussian processes2009
- Model-order selectionIEEE Signal Processing Magazine, 2004