Efficient learning methods for large-scale optimal inversion design

10/06/2021
by   Julianne Chung, et al.
0

In this work, we investigate various approaches that use learning from training data to solve inverse problems, following a bi-level learning approach. We consider a general framework for optimal inversion design, where training data can be used to learn optimal regularization parameters, data fidelity terms, and regularizers, thereby resulting in superior variational regularization methods. In particular, we describe methods to learn optimal p and q norms for L^p- L^q regularization and methods to learn optimal parameters for regularization matrices defined by covariance kernels. We exploit efficient algorithms based on Krylov projection methods for solving the regularized problems, both at training and validation stages, making these methods well-suited for large-scale problems. Our experiments show that the learned regularization methods perform well even when there is some inexactness in the forward operator, resulting in a mixture of model and measurement error.

READ FULL TEXT

page 12

page 15

page 16

page 17

page 18

page 21

page 22

research
02/21/2021

Improve Unscented Kalman Inversion With Low-Rank Approximation and Reduced-Order Model

The unscented Kalman inversion (UKI) presented in [1] is a general deriv...
research
12/23/2021

Learning multiple regularization parameters for generalized Tikhonov regularization using multiple data sets without true data

During the inversion of discrete linear systems, noise in data can be am...
research
03/30/2020

Hybrid Projection Methods for Large-scale Inverse Problems with Mixed Gaussian Priors

When solving ill-posed inverse problems, a good choice of the prior is c...
research
04/14/2021

Learning Regularization Parameters of Inverse Problems via Deep Neural Networks

In this work, we describe a new approach that uses deep neural networks ...
research
11/14/2020

On the relation between constraint regularization, level sets, and shape optimization

We consider regularization methods based on the coupling of Tikhonov reg...
research
02/21/2020

Joint geophysical, petrophysical and geologic inversion using a dynamic Gaussian mixture model

We present a framework for petrophysically and geologically guided inver...
research
06/14/2022

Hybrid Projection Methods for Solution Decomposition in Large-scale Bayesian Inverse Problems

We develop hybrid projection methods for computing solutions to large-sc...

Please sign up or login with your details

Forgot password? Click here to reset