A New Convergence Analysis of Plug-and-Play Proximal Gradient Descent Under Prior Mismatch

TL;DR

This paper introduces a novel convergence analysis for plug-and-play proximal gradient descent (PnP-PGD) when the denoiser is trained on a different data distribution, removing previous restrictive assumptions and extending to equivariant PnP.

Contribution

It provides the first convergence proof of PnP-PGD under prior mismatch and extends the theory to equivariant PnP, improving error bounds.

Findings

First convergence proof of PnP-PGD under prior mismatch

Removal of restrictive assumptions in existing theory

Tighter convergence bounds for equivariant PnP

Abstract

In this work, we provide a new convergence theory for plug-and-play proximal gradient descent (PnP-PGD) under prior mismatch where the denoiser is trained on a different data distribution to the inference task at hand. To the best of our knowledge, this is the first convergence proof of PnP-PGD under prior mismatch. Compared with the existing theoretical results for PnP algorithms, our new results removed the need for several restrictive and unverifiable assumptions. Moreover, we derive the convergence theory for equivariant PnP (EPnP) under the prior mismatch setting, proving that EPnP reduces error variance and explicitly tightens the convergence bound.