Bayesian neural network priors for edge-preserving inversion

DOI10.3934/ipi.2022022OpenAlexW4226090664MaRDI QIDQ2674903

Yanyan Li

Publication date: 14 September 2022

Published in: Inverse Problems and Imaging (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2112.10663

zbMATH Keywords

inverse problemsdeblurring\(\alpha\)-stable distributionBayesian priorsBayesian neural networks

Mathematics Subject Classification ID

Infinitely divisible distributions; stable distributions (60E07) Artificial neural networks and deep learning (68T07) Bayesian inference (62F15) Monte Carlo methods (65C05)

Related Items (3)

Bayesian inversion with α-stable priors ⋮ Deep stable neural networks: large-width asymptotics and convergence rates ⋮ Horseshoe Priors for Edge-Preserving Linear Bayesian Inversion

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Besov priors for Bayesian inverse problems
• Spectral gaps for a Metropolis-Hastings algorithm in infinite dimensions
• Ensembling neural networks: Many could be better than all
• Geometric MCMC for infinite-dimensional inverse problems
• Isotropic and anisotropic total variation regularization in electrical impedance tomography
• Statistical and computational inverse problems.
• Bayesian learning for neural networks
• Well-posed Bayesian inverse problems and heavy-tailed stable quasi-Banach space priors
• Cauchy Markov random field priors for Bayesian inversion
• On the convergence of the Laplace approximation and noise-level-robustness of Laplace-based Monte Carlo methods for Bayesian inverse problems
• Discretization-invariant Bayesian inversion and Besov space priors
• Cauchy difference priors for edge-preserving Bayesian inversion
• Statistical inverse problems: discretization, model reduction and inverse crimes
• Well-posed stochastic extensions of ill-posed linear problems
• Inverse problems: A Bayesian perspective
• Approximation of Bayesian Inverse Problems for PDEs
• Can one use total variation prior for edge-preserving Bayesian inversion?
• Statistical Tools for Finance and Insurance
• Optimal Approximation with Sparsely Connected Deep Neural Networks
• A Computational Framework for Infinite-Dimensional Bayesian Inverse Problems Part I: The Linearized Case, with Application to Global Seismic Inversion
• MCMC methods for functions: modifying old algorithms to make them faster

This page was built for publication: Bayesian neural network priors for edge-preserving inversion