Bayesian Inverse Problems with Conditional Sinkhorn Generative Adversarial Networks in Least Volume Latent Spaces

TL;DR

This paper introduces a novel approach combining Least Volume dimension reduction with conditional Sinkhorn GANs to improve Bayesian inverse problem solving in high-dimensional, nonlinear, and uncertain settings.

Contribution

It presents a new latent space reduction method that enables efficient training of conditional GANs for complex inverse problems.

Findings

Effective dimension reduction improves model training

Method successfully applied to ODE parameter inversion

Enhanced posterior inference in high-dimensional flow problems

Abstract

Solving inverse problems in scientific and engineering fields has long been intriguing and holds great potential for many applications, yet most techniques still struggle to address issues such as high dimensionality, nonlinearity and model uncertainty inherent in these problems. Recently, generative models such as Generative Adversarial Networks (GANs) have shown great potential in approximating complex high dimensional conditional distributions and have paved the way for characterizing posterior densities in Bayesian inverse problems, yet the problems' high dimensionality and high nonlinearity often impedes the model's training. In this paper we show how to tackle these issues with Least Volume--a novel unsupervised nonlinear dimension reduction method--that can learn to represent the given datasets with the minimum number of latent variables while estimating their intrinsic dimensions. Once the low dimensional latent spaces are identified, efficient and accurate training of conditional generative models becomes feasible, resulting in a latent conditional GAN framework for posterior inference. We demonstrate the power of the proposed methodology on a variety of applications including inversion of parameters in systems of ODEs and high dimensional hydraulic conductivities in subsurface flow problems, and reveal the impact of the observables' and unobservables' intrinsic dimensions on inverse problems.