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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Takahashi, Takashi, Kabashima, Yoshiyuki
Format: Preprint
Published: 2020
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915423956500480
author Takahashi, Takashi
Kabashima, Yoshiyuki
author_facet Takahashi, Takashi
Kabashima, Yoshiyuki
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2001_02824
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle Macroscopic Analysis of Vector Approximate Message Passing in a Model Mismatch Setting
Takahashi, Takashi
Kabashima, Yoshiyuki
Information Theory
Disordered Systems and Neural Networks
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.
title Macroscopic Analysis of Vector Approximate Message Passing in a Model Mismatch Setting
topic Information Theory
Disordered Systems and Neural Networks
url https://arxiv.org/abs/2001.02824