Stein variational reduced basis Bayesian inversion

02/25/2020
by   Peng Chen, et al.
0

We propose and analyze a Stein variational reduced basis method (SVRB) to solve large-scale PDE-constrained Bayesian inverse problems. To address the computational challenge of drawing numerous samples requiring expensive PDE solves from the posterior distribution, we integrate an adaptive and goal-oriented model reduction technique with an optimization-based Stein variational gradient descent method (SVGD). The samples are drawn from the prior distribution and iteratively pushed to the posterior by a sequence of transport maps, which are constructed by SVGD, requiring the evaluation of the potential—the negative log of the likelihood function—and its gradient with respect to the random parameters, which depend on the solution of the PDE. To reduce the computational cost, we develop an adaptive and goal-oriented model reduction technique based on reduced basis approximations for the evaluation of the potential and its gradient. We present a detailed analysis for the reduced basis approximation errors of the potential and its gradient, the induced errors of the posterior distribution measured by Kullback–Leibler divergence, as well as the errors of the samples. To demonstrate the computational accuracy and efficiency of SVRB, we report results of numerical experiments on a Bayesian inverse problem governed by a diffusion PDE with random parameters with both uniform and Gaussian prior distributions. Over 100X speedups can be achieved while the accuracy of the approximation of the potential and its gradient is preserved.

READ FULL TEXT

page 18

page 28

research
09/27/2017

Multilevel Sequential^2 Monte Carlo for Bayesian Inverse Problems

The identification of parameters in mathematical models using noisy obse...
research
02/26/2021

Data-Free Likelihood-Informed Dimension Reduction of Bayesian Inverse Problems

Identifying a low-dimensional informed parameter subspace offers a viabl...
research
03/01/2023

Dimension-reduced KRnet maps for high-dimensional Bayesian inverse problems

We present a dimension-reduced KRnet map approach (DR-KRnet) for high-di...
research
04/13/2021

An acceleration strategy for randomize-then-optimize sampling via deep neural networks

Randomize-then-optimize (RTO) is widely used for sampling from posterior...
research
02/09/2020

Projected Stein Variational Gradient Descent

The curse of dimensionality is a critical challenge in Bayesian inferenc...
research
04/12/2019

Bayesian inversion for nanowire field-effect sensors

Nanowire field-effect sensors have recently been developed for label-fre...
research
04/13/2021

Stein variational gradient descent with local approximations

Bayesian computation plays an important role in modern machine learning ...

Please sign up or login with your details

Forgot password? Click here to reset