Stability of Gibbs Posteriors from the Wasserstein Loss for Bayesian Full Waveform Inversion

DOI10.1137/20M1334218zbMath1473.62018arXiv2004.03730OpenAlexW3208551383MaRDI QIDQ5158929

Matthew M. Dunlop, Yunan Yang

Publication date: 26 October 2021

Published in: SIAM/ASA Journal on Uncertainty Quantification (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2004.03730

zbMATH Keywords

Wasserstein metricBayesian inferenceprior distributionseismic inversionGibbs posterior

Mathematics Subject Classification ID

Bayesian problems; characterization of Bayes procedures (62C10) Sensitivity, stability, well-posedness (49K40) Inverse problems in geophysics (86A22) Numerical solution to inverse problems in abstract spaces (65J22)

Related Items (6)

Optimal Transport for Parameter Identification of Chaotic Dynamics via Invariant Measures ⋮ Applications of optimal transportation in the natural sciences. Abstracts from the workshop held February 21--27, 2021 (online meeting) ⋮ Norm-dependent convergence and stability of the inverse scattering series for diffuse and scalar waves ⋮ Generalized Bayes approach to inverse problems with model misspecification ⋮ Implicit regularization effects of the Sobolev norms in image processing ⋮ Object based Bayesian full-waveform inversion for shear elastography

Cites Work

• Unnamed Item
• A Bayesian level set method for geometric inverse problems
• Optimal transport for seismic full waveform inversion
• Application of the Wasserstein metric to seismic signals
• Bayesian inference with optimal maps
• Scalable and efficient algorithms for the propagation of uncertainty from data through inference to prediction for large-scale problems, with application to flow of the antarctic ice sheet
• A new class of transport distances between measures
• Generalization of an inequality by Talagrand and links with the logarithmic Sobolev inequality
• Geometric MCMC for infinite-dimensional inverse problems
• Hierarchical Bayesian level set inversion
• Well-posed Bayesian inverse problems and heavy-tailed stable quasi-Banach space priors
• On the convergence of the Laplace approximation and noise-level-robustness of Laplace-based Monte Carlo methods for Bayesian inverse problems
• An optimal transport approach for seismic tomography: application to 3D full waveform inversion
• On the properties of variational approximations of Gibbs posteriors
• Uncertainty Quantification in Graph-Based Classification of High Dimensional Data
• Absorbing boundary conditions for numerical simulation of waves
• Bayesian inversion in resin transfer molding
• Inference for Empirical Wasserstein Distances on Finite Spaces
• Inverse Problem Theory and Methods for Model Parameter Estimation
• On the Well-posedness of Bayesian Inverse Problems
• Calibrating general posterior credible regions
• The quadratic Wasserstein metric for inverse data matching
• WASSERSTEIN METRIC-DRIVEN BAYESIAN INVERSION WITH APPLICATIONS TO SIGNAL PROCESSING
• Reconciling Bayesian and Perimeter Regularization for Binary Inversion
• Comparison between W₂ distance and Ḣ⁻¹ norm, and Localization of Wasserstein distance

This page was built for publication: Stability of Gibbs Posteriors from the Wasserstein Loss for Bayesian Full Waveform Inversion