Log In Sign Up

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

by   Matthew M. Dunlop, et al.

Recently, the Wasserstein loss function has been proven to be effective when applied to deterministic full-waveform inversion (FWI) problems. We consider the application of this loss function in Bayesian FWI so that the uncertainty can be captured in the solution. Other loss functions that are commonly used in practice are also considered for comparison. Existence and stability of the resulting Gibbs posteriors are shown on function space under weak assumptions on the prior and model. In particular, the distribution arising from the Wasserstein loss is shown to be quite stable with respect to high-frequency noise in the data. We then illustrate the difference between the resulting distributions numerically, using Laplace approximations and dimension-robust MCMC to estimate the unknown velocity field and uncertainty associated with the estimates.


page 9

page 22

page 23

page 24

page 25

page 26


ML-misfit: Learning a robust misfit function for full-waveform inversion using machine learning

Most of the available advanced misfit functions for full waveform invers...

Adaptive particle-based approximations of the Gibbs posterior for inverse problems

In this work, we adopt a general framework based on the Gibbs posterior ...

On Reparameterization Invariant Bayesian Point Estimates and Credible Regions

This paper considers reparameterization invariant Bayesian point estimat...

Bayesian neural network priors for edge-preserving inversion

We consider Bayesian inverse problems wherein the unknown state is assum...

WPPNets: Unsupervised CNN Training with Wasserstein Patch Priors for Image Superresolution

We introduce WPPNets, which are CNNs trained by a new unsupervised loss ...

Uncertainty in Neural Relational Inference Trajectory Reconstruction

Neural networks used for multi-interaction trajectory reconstruction lac...