On maximum a posteriori estimation with Plug \& Play priors and stochastic gradient descent
From MaRDI portal
Publication:6155451
denoisinginverse problemsdeblurringinpaintingstochastic gradient descentBayesian imagingPlug and Play
Bayesian inference (62F15) Numerical mathematical programming methods (65K05) Numerical optimization and variational techniques (65K10) Bayesian problems; characterization of Bayes procedures (62C10) Analysis of algorithms and problem complexity (68Q25) Nonconvex programming, global optimization (90C26) Computing methodologies for image processing (68U10) Computer science (68-XX) Information and communication theory, circuits (94-XX)
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.
Recommendations
- Approximate maximum a posteriori with Gaussian process priors
- scientific article; zbMATH DE number 6860839
- Learning maximum a-posteriori perturbation models
- Generalized gradients: priors on minimization flows
- A posteriori minimax estimation with likelihood constraints
- Learning to optimize via posterior sampling
- A Bayesian conjugate gradient method (with discussion)
- A Probabilistic Approach to Gradient Estimates
- A recursive maximum a posteriori estimator
- scientific article; zbMATH DE number 7219341
Cites work
- scientific article; zbMATH DE number 1461253 (Why is no real title available?)
- scientific article; zbMATH DE number 1432028 (Why is no real title available?)
- A Convergent Image Fusion Algorithm Using Scene-Adapted Gaussian-Mixture-Based Denoising
- A Review of Image Denoising Algorithms, with a New One
- A first-order primal-dual algorithm for convex problems with applications to imaging
- A nonlocal Bayesian image denoising algorithm
- Accelerating Proximal Markov Chain Monte Carlo by Using an Explicit Stabilized Method
- An algorithm for total variation minimization and applications
- Applications of a Kushner and Clark lemma to general classes of stochastic algorithms
- Asymptotic bias of stochastic gradient search
- Bayesian Imaging Using Plug & Play Priors: When Langevin Meets Tweedie
- Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising
- Breaking the curse of dimensionality with convex neural networks
- Convergence of a stochastic approximation version of the EM algorithm
- Convex analysis and monotone operator theory in Hilbert spaces
- Convex optimization: algorithms and complexity
- De-noising by soft-thresholding
- DeepISP: Toward Learning an End-to-End Image Processing Pipeline
- Distributed optimization and statistical learning via the alternating direction method of multipliers
- Do stochastic algorithms avoid traps?
- Efficient Bayesian computation by proximal Markov chain Monte Carlo: when Langevin meets Moreau
- General results on the convergence of stochastic algorithms
- Learning maximally monotone operators for image recovery
- Lectures on convex optimization
- Maximum likelihood estimation of regularization parameters in high-dimensional inverse problems: an empirical Bayesian approach. I: Methodology and experiments
- Maximum-a-posteriori estimation with Bayesian confidence regions
- Nonlinear total variation based noise removal algorithms
- Optimization methods for large-scale machine learning
- Plug-and-Play Unplugged: Optimization-Free Reconstruction Using Consensus Equilibrium
- Posterior expectation of the total variation model: properties and experiments
- Proximal splitting methods in signal processing
- Scalable Bayesian uncertainty quantification in imaging inverse problems via convex optimization
- Should Penalized Least Squares Regression be Interpreted as Maximum A Posteriori Estimation?
- Solving Inverse Problems With Piecewise Linear Estimators: From Gaussian Mixture Models to Structured Sparsity
- Solving inverse problems using data-driven models
- Symmetrizing smoothing filters
- The Bayesian Choice
- The Little Engine that Could: Regularization by Denoising (RED)
- Tweedie’s Formula and Selection Bias
This page was built for publication: On maximum a posteriori estimation with Plug \& Play priors and stochastic gradient descent
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6155451)
