Nonasymptotic Convergence Rates for Plug-and-Play Methods With MMSE Denoisers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pritchard, Henry, Parhi, Rahul
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908934006112256
author Pritchard, Henry
Parhi, Rahul
author_facet Pritchard, Henry
Parhi, Rahul
contents It is known that the minimum-mean-squared-error (MMSE) denoiser under Gaussian noise can be written as a proximal operator, which suffices for asymptotic convergence of plug-and-play (PnP) methods but does not reveal the structure of the induced regularizer or give convergence rates. We show that the MMSE denoiser corresponds to a regularizer that can be written explicitly as an upper Moreau envelope of the negative log-marginal density, which in turn implies that the regularizer is 1-weakly convex. Using this property, we derive (to the best of our knowledge) the first sublinear convergence guarantee for PnP proximal gradient descent with an MMSE denoiser. We validate the theory with a one-dimensional synthetic study that recovers the implicit regularizer. We also validate the theory with imaging experiments (deblurring and computed tomography), which exhibit the predicted sublinear behavior.
format Preprint
id arxiv_https___arxiv_org_abs_2510_27211
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Nonasymptotic Convergence Rates for Plug-and-Play Methods With MMSE Denoisers
Pritchard, Henry
Parhi, Rahul
Optimization and Control
Signal Processing
Machine Learning
It is known that the minimum-mean-squared-error (MMSE) denoiser under Gaussian noise can be written as a proximal operator, which suffices for asymptotic convergence of plug-and-play (PnP) methods but does not reveal the structure of the induced regularizer or give convergence rates. We show that the MMSE denoiser corresponds to a regularizer that can be written explicitly as an upper Moreau envelope of the negative log-marginal density, which in turn implies that the regularizer is 1-weakly convex. Using this property, we derive (to the best of our knowledge) the first sublinear convergence guarantee for PnP proximal gradient descent with an MMSE denoiser. We validate the theory with a one-dimensional synthetic study that recovers the implicit regularizer. We also validate the theory with imaging experiments (deblurring and computed tomography), which exhibit the predicted sublinear behavior.
title Nonasymptotic Convergence Rates for Plug-and-Play Methods With MMSE Denoisers
topic Optimization and Control
Signal Processing
Machine Learning
url https://arxiv.org/abs/2510.27211