ICASSP 2026, IEEE International Conference on Acoustics, Speech, and Signal Processing, 4-8 May 2026, Barcelona, Spain
Generalized Approximate Message Passing (GAMP) enables Bayesian inference in linear models with non-identically and independently distributed (n.i.i.d.) priors and n.i.i.d. measurements of the linear mixture outputs. It represents an efficient technique for approximate inference, which becomes accurate when both rows and columns of the measurement matrix can be treated as sets of independent vectors and both dimensions become large. The fixed points of GAMP correspond to the extrema of a large system limit of the Bethe Free Energy (LSL-BFE), which represents a meaningful approximation criterion regardless of whether the measurement matrix exhibits the independence properties. However, the convergence of (G)AMP can be problematic for certain measurement matrices. In this paper, we revisit the LSL-BFE and its Lagrangian function. We derive an augmented GAMP algorithm by alternately enforcing the Karush-Kuhn-Tucker (KKT) conditions, called KKT-GAMP (KGAMP). To avoid matrix inversions, we introduce Adaptive (Accelerated) Gradient Descent (A(A)GD) techniques. Analysis shows convergence under relaxed conditions. Simulations indicate accelerated convergence compared to existing low complexity methods and illustrate the importance of adaptation.
Type:
Conférence
City:
Barcelona
Date:
2026-05-04
Department:
Systèmes de Communication
Eurecom Ref:
8685
Copyright:
© 2026 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
See also:
