Hybrid Approximate Message Passing

DOI10.1109/TSP.2017.2713759MaRDI QIDQ4621837zbMATH OpenOpenAlexFDO

Authors Sundeep Rangan, Alyson K. Fletcher, Vivek K. Goyal, Evan Byrne, Philip Schniter

Publication date 8 February 2019

Published in IEEE Transactions on Signal Processing (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1111.2581

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Abstract: Gaussian and quadratic approximations of message passing algorithms on graphs have attracted considerable recent attention due to their computational simplicity, analytic tractability, and wide applicability in optimization and statistical inference problems. This paper presents a systematic framework for incorporating such approximate message passing (AMP) methods in general graphical models. The key concept is a partition of dependencies of a general graphical model into strong and weak edges, with the weak edges representing interactions through aggregates of small, linearizable couplings of variables. AMP approximations based on the Central Limit Theorem can be readily applied to aggregates of many weak edges and integrated with standard message passing updates on the strong edges. The resulting algorithm, which we call hybrid generalized approximate message passing (HyGAMP), can yield significantly simpler implementations of sum-product and max-sum loopy belief propagation. By varying the partition of strong and weak edges, a performance--complexity trade-off can be achieved. Group sparsity and multinomial logistic regression problems are studied as examples of the proposed methodology.

Recommendations

• Vector Approximate Message Passing
• A Unifying Tutorial on Approximate Message Passing
• Expectation-Maximization Gaussian-Mixture Approximate Message Passing
• Approximate Message Passing Algorithm With Universal Denoising and Gaussian Mixture Learning
• Multi-Layer Bilinear Generalized Approximate Message Passing
• On the Convergence of Approximate Message Passing With Arbitrary Matrices
• Approximate Message Passing With Consistent Parameter Estimation and Applications to Sparse Learning
• Message-passing algorithms for inference and optimization
• Universality of approximate message passing algorithms

Cited in

(2)

• Plug in estimation in high dimensional linear inverse problems a rigorous analysis
• A Unifying Tutorial on Approximate Message Passing

This page was built for publication: Hybrid Approximate Message Passing

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4621837)