Provable Convergence of Plug-and-Play Priors with MMSE denoisers

Abstract

Plug-and-play priors (PnP) is a methodology for regularized image reconstruction that specifies the prior through an image denoiser. While PnP algorithms are well understood for denoisers performing maximum a posteriori probability (MAP) estimation, they have not been analyzed for the minimum mean squared error (MMSE) denoisers. This letter addresses this gap by establishing the first theoretical convergence result for the iterative shrinkage/thresholding algorithm (ISTA) variant of PnP for MMSE denoisers. We show that the iterates produced by PnP-ISTA with an MMSE denoiser converge to a stationary point of some global cost function. We validate our analysis on sparse signal recovery in compressive sensing by comparing two types of denoisers, namely the exact MMSE denoiser and the approximate MMSE denoiser obtained by training a deep neural net.

References in corpus (2)

• Probabilistic Reconstruction in Compressed Sensing: Algorithms, Phase Diagrams, and Threshold Achieving Matrices
• Plug-and-play ISTA converges with kernel denoisers

Cited by in corpus (9)

• Plug-and-Play Methods for Integrating Physical and Learned Models in Computational Imaging
• Fixed-Point and Objective Convergence of Plug-and-Play Algorithms
• On Plug-and-Play Regularization using Linear Denoisers
• SGD-Net: Efficient Model-Based Deep Learning with Theoretical Guarantees
• Plug-and-Play Quantum Adaptive Denoiser for Deconvolving Poisson Noisy Images
• Provable Preconditioned Plug-and-Play Approach for Compressed Sensing MRI Reconstruction
• On the Contractivity of Plug-and-Play Operators
• Monotone Lipschitz-Gradient Denoiser: Explainability of Operator Regularization Approaches Free From Lipschitz Constant Control
• Provably Convergent Plug & Play Linearized ADMM, applied to Deblurring Spatially Varying Kernels