A New Convergence Analysis of Plug-and-Play Proximal Gradient Descent Under Prior Mismatch
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 17 references that are in the map. First posted on arXiv 14 Jan 2026.
Builds on
14 of 17 references.
References · 14
- 2018On the Spectral Bias of Neural Networkscited by 1,341
- 2017Deep Image Priorcited by 1,098
- 2019Making Convolutional Networks Shift-Invariant Againcited by 391
- 2014Understanding image representations by measuring their equivariance and equivalencecited by 243
- 2019On instabilities of deep learning in image reconstruction - Does AI come at a cost?cited by 212
- 2019Plug-and-Play Methods Provably Converge with Properly Trained Denoiserscited by 198
- 2021Gradient Step Denoiser for convergent Plug-and-Playcited by 108
- 2022Proximal Denoiser for Convergent Plug-and-Play Optimization with Nonconvex Regularizationcited by 80
- 2016Inductive Bias of Deep Convolutional Networks through Pooling Geometrycited by 53
- 2020Provable Convergence of Plug-and-Play Priors with MMSE denoiserscited by 39
- 2018A characterization of proximity operatorscited by 32
- 2023Provably Convergent Plug-and-Play Quasi-Newton Methodscited by 15
Built on by
Not cited yet.