Sparsity promoting hybrid solvers for hierarchical Bayesian inverse problems

by   Daniela Calvetti, et al.

The recovery of sparse generative models from few noisy measurements is an important and challenging problem. Many deterministic algorithms rely on some form of ℓ_1-ℓ_2 minimization to combine the computational convenience of the ℓ_2 penalty and the sparsity promotion of the ℓ_1. It was recently shown within the Bayesian framework that sparsity promotion and computational efficiency can be attained with hierarchical models with conditionally Gaussian priors and gamma hyperpriors. The related Gibbs energy function is a convex functional and its minimizer, which is the MAP estimate of the posterior, can be computed efficiently with the globally convergent Iterated Alternating Sequential (IAS) algorithm <cit.>. Generalization of the hyperpriors for these sparsity promoting hierarchical models to generalized gamma family yield either globally convex Gibbs energy functionals, or can exhibit local convexity for some choices for the hyperparameters. <cit.>. The main problem in computing the MAP solution for greedy hyperpriors that strongly promote sparsity is the presence of local minima. To overcome the premature stopping at a spurious local minimizer, we propose two hybrid algorithms that first exploit the global convergence associated with gamma hyperpriors to arrive in a neighborhood of the unique minimizer, then adopt a generalized gamma hyperprior that promote sparsity more strongly. The performance of the two algorithms is illustrated with computed examples.


page 15

page 16

page 17

page 18

page 19


Hybrid solver for hierarchical Bayesian inverse problems

The recovery of sparse generative models from few noisy measurements is ...

Hierarchical Ensemble Kalman Methods with Sparsity-Promoting Generalized Gamma Hyperpriors

This paper introduces a computational framework to incorporate flexible ...

Path-following methods for Maximum a Posteriori estimators in Bayesian hierarchical models: How estimates depend on hyperparameters

Maximum a posteriori (MAP) estimation, like all Bayesian methods, depend...

Sparsity promoting reconstructions via hierarchical prior models in diffuse optical tomography

Diffuse optical tomography (DOT) is a severely ill-posed nonlinear inver...

Overcomplete representation in a hierarchical Bayesian framework

A common task in inverse problems and imaging is finding a solution that...

Computationally efficient sampling methods for sparsity promoting hierarchical Bayesian models

Bayesian hierarchical models have been demonstrated to provide efficient...

A Bayesian approach for partial Gaussian graphical models with sparsity

We explore various Bayesian approaches to estimate partial Gaussian grap...

Please sign up or login with your details

Forgot password? Click here to reset