Saved in:
Bibliographic Details
Main Authors: Wadayama, Tadashi, Takahashi, Takumi
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.07095
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917195778359296
author Wadayama, Tadashi
Takahashi, Takumi
author_facet Wadayama, Tadashi
Takahashi, Takumi
contents We propose score-based VAMP (SC-VAMP), a variant of vector approximate message passing (VAMP) in which the Onsager correction is expressed and computed via conditional Fisher information, thereby enabling a Jacobian-free implementation. Using learned score functions, SC-VAMP constructs nonlinear MMSE estimators through Tweedie's formula and derives the corresponding Onsager terms from the score-norm statistics, avoiding the need for analytical derivatives of the prior or likelihood. When combined with random orthogonal/unitary mixing to mitigate non-ideal, structured or correlated sensing settings, the proposed framework extends VAMP to complex black-box inference problems where explicit modeling is intractable. Finally, by leveraging the entropic CLT, we provide an information-theoretic perspective on the Gaussian approximation underlying SE, offering insight into the decoupling principle beyond idealized i.i.d. settings, including nonlinear regimes.
format Preprint
id arxiv_https___arxiv_org_abs_2601_07095
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Score-Based VAMP with Fisher-Information-Based Onsager Correction
Wadayama, Tadashi
Takahashi, Takumi
Information Theory
We propose score-based VAMP (SC-VAMP), a variant of vector approximate message passing (VAMP) in which the Onsager correction is expressed and computed via conditional Fisher information, thereby enabling a Jacobian-free implementation. Using learned score functions, SC-VAMP constructs nonlinear MMSE estimators through Tweedie's formula and derives the corresponding Onsager terms from the score-norm statistics, avoiding the need for analytical derivatives of the prior or likelihood. When combined with random orthogonal/unitary mixing to mitigate non-ideal, structured or correlated sensing settings, the proposed framework extends VAMP to complex black-box inference problems where explicit modeling is intractable. Finally, by leveraging the entropic CLT, we provide an information-theoretic perspective on the Gaussian approximation underlying SE, offering insight into the decoupling principle beyond idealized i.i.d. settings, including nonlinear regimes.
title Score-Based VAMP with Fisher-Information-Based Onsager Correction
topic Information Theory
url https://arxiv.org/abs/2601.07095