Skip to Main content Skip to Navigation
New interface
Preprints, Working Papers, ...

On Maximum-a-Posteriori estimation with Plug & Play priors and stochastic gradient descent

Abstract : Bayesian methods to solve imaging inverse problems usually combine an explicit data likelihood function with a prior distribution that explicitly models expected properties of the solution. Many kinds of priors have been explored in the literature, from simple ones expressing local properties to more involved ones exploiting image redundancy at a non-local scale. In a departure from explicit modelling, several recent works have proposed and studied the use of implicit priors defined by an image denoising algorithm. This approach, commonly known as Plug & Play (PnP) regularisation, can deliver remarkably accurate results, particularly when combined with state-of-the-art denoisers based on convolutional neural networks. However, the theoretical analysis of PnP Bayesian models and algorithms is difficult and works on the topic often rely on unrealistic assumptions on the properties of the image denoiser. This papers studies maximum-a-posteriori (MAP) estimation for Bayesian models with PnP priors. We first consider questions related to existence, stability and well-posedness, and then present a convergence proof for MAP computation by PnP stochastic gradient descent (PnP-SGD) under realistic assumptions on the denoiser used. We report a range of imaging experiments demonstrating PnP-SGD as well as comparisons with other PnP schemes.
Complete list of metadata

https://hal.archives-ouvertes.fr/hal-03348735
Contributor : Rémi Laumont Connect in order to contact the contributor
Submitted on : Thursday, July 21, 2022 - 5:48:56 PM
Last modification on : Friday, August 5, 2022 - 2:58:08 PM

File

Manuscript.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-03348735, version 2
  • ARXIV : 2201.06133

Citation

Rémi Laumont, Valentin de Bortoli, Andrés Almansa, Julie Delon, Alain Durmus, et al.. On Maximum-a-Posteriori estimation with Plug & Play priors and stochastic gradient descent. 2022. ⟨hal-03348735v2⟩

Share

Metrics

Record views

206

Files downloads

160