Hilbert-Scale Stability of Posterior Diffusion Priors for Ill-Posed Signal Recovery
Abstract
Indirect and noisy observations are difficult to invert when the forward operator smooths out the unknown signal. In this case, the unstable modes are precisely the modes that the data reveals least, thus the success of any reconstruction method depends on how prior information interacts with the geometry of the operator across regularity scales. Diffusion priors have become ubiquitous for such problems; however, the current theory still does not determine when a learned score remains informative under ill-posed forward operators. In this paper, we study posterior diffusion for linear inverse problems on Hilbert scales and derive a stability theory under an explicit score-amplification condition. Under a smoothing condition on the forward map, a source condition on the truth, and weak-norm control of score error, we derive non-asymptotic recovery bounds in Hss that separate observation noise, score approximation, and reverse-time discretization. These bounds give a recoverable regularity threshold determined jointly by operator smoothing, truth regularity, score regularity, and the posterior correction. The threshold specifies the Hilbert-scale norms Hss in which weak-norm score error remains controlled after propagation through the posterior reverse dynamics. For larger regularity indices s, the inverse geometry magnifies the same error, and the Hilbert-scale recovery estimate no longer gives uniform stability. We also prove that a posterior correction adapted to the forward operator improves stability relative to isotropic guidance in the regularity ranges where the smoothing action of the forward map matters most. The recovery estimates give a regularity-sensitive theory of posterior diffusion and show how learned score error, operator smoothing, and reconstruction norm jointly determine the stable range predicted by the analysis.
Related
- A Posterior-Dynamics Framework for Imaging Inverse Problems with Pretrained Diffusion Priors
- Kinetic Langevin Meets Split Gibbs: Accelerated Posterior Sampling for Imaging Inverse Problems with Diffusion Priors
- Stability Estimates for the Inverse Recovery of Drift and Diffusion Point Sources in Stochastic Parabolic Equations
- Sieve-free ReLU Bayesian priors with near-minimax posterior contraction
- Bayesian Operator Learning: Posterior Existence and Convergence of Point Estimates for Gaussian Priors
BibTeX
@misc{moraffah2026hilbertscale,
title = {{Hilbert-Scale Stability of Posterior Diffusion Priors for Ill-Posed Signal Recovery}},
author = {Bahman Moraffah and Raha Moraffah},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.27030},
eprint = {2610.27030},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.27030},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Hilbert-Scale Stability of Posterior Diffusion Priors for Ill-Posed Signal Recovery
AU - Bahman Moraffah
AU - Raha Moraffah
PY - 2026
DA - 2026/10/27
PB - arXiv
DO - 10.48550/arxiv.2610.27030
UR - https://arxiv.org/abs/2610.27030
AB - Indirect and noisy observations are difficult to invert when the forward operator smooths out the unknown signal. In this case, the unstable modes are precisely the modes that the data reveals least, thus the success of any reconstruction method depends on how prior information interacts with the geometry of the operator across regularity scales. Diffusion priors have become ubiquitous for such problems; however, the current theory still does not determine when a learned score remains informative under ill-posed forward operators. In this paper, we study posterior diffusion for linear inverse problems on Hilbert scales and derive a stability theory under an explicit score-amplification condition. Under a smoothing condition on the forward map, a source condition on the truth, and weak-norm control of score error, we derive non-asymptotic recovery bounds in Hs^s that separate observation noise, score approximation, and reverse-time discretization. These bounds give a recoverable regularity threshold determined jointly by operator smoothing, truth regularity, score regularity, and the posterior correction. The threshold specifies the Hilbert-scale norms Hs^s in which weak-norm score error remains controlled after propagation through the posterior reverse dynamics. For larger regularity indices s, the inverse geometry magnifies the same error, and the Hilbert-scale recovery estimate no longer gives uniform stability. We also prove that a posterior correction adapted to the forward operator improves stability relative to isotropic guidance in the regularity ranges where the smoothing action of the forward map matters most. The recovery estimates give a regularity-sensitive theory of posterior diffusion and show how learned score error, operator smoothing, and reconstruction norm jointly determine the stable range predicted by the analysis.
ER -