Graphs, Games, Sparsity, and Signal Processing
G.3.4
Lecture
Compressed Sensing

Macroscopic Analysis of Vector Approximate Message Passing in a Model Mismatch Setting

Takashi Takahashi, Yoshiyuki Kabashima

Date & Time

01:00 am – 01:00 am

Abstract

Vector approximate message passing (VAMP) is an efficient approximate inference algorithm used for generalized linear models. Although VAMP exhibits excellent performance, particularly when measurement matrices are sampled from rotationally invariant ensembles, existing convergence and performance analyses have been limited mostly to cases in which the correct posterior distribution is available. Here, we extend the analyses for cases in which the correct posterior distribution is not used in the inference stage. We derive state evolution equations, which macroscopically describe the dynamics of VAMP, and show that their fixed point is consistent with the replica symmetric solution obtained by the replica method of statistical mechanics. We also show that the fixed point of VAMP can exhibit a microscopic instability, the critical condition of which agrees with that for breaking the replica symmetry. The results of numerical experiments support our findings.


Presenters

Takashi Takahashi

Tokyo Institute of Technology

Yoshiyuki Kabashima

The University of Tokyo

Session Chair

Sundeep Rangan

New York University