An adaptive surrogate modeling based on deep neural networks for large-scale Bayesian inverse problems

11/20/2019
by   Liang Yan, et al.
0

It is popular approaches to use surrogate models to speed up the computational procedure for Bayesian inverse problems (BIPs). For instance, the polynomial chaos expansions (PCE) are often combined with the Markov chain Monte Carlo sampling to accelerate the online computations. While this approach can be very efficient, there exist, however, two main limitations: (i) the PCE surrogate admits limitations to handle problems with low regularity; (ii) the PCE surrogate suffers from the so called curse of dimensionality. To this end, we present in this work an adaptive multi-fidelity deep neural networks (DNNs) based surrogate modeling for large-scale BIPs, motivated by the facts that the DNNs can potentially handle functions with limited regularity and are powerful tools for high dimensional problems. More precisely, we begin with a low fidelity DNN-surrogate and then correct it adaptively using online high fidelity data. The key idea is to view the low fidelity surrogate as an input variable into the DNN-surrogate of the next iteration – yielding a composite DNN that combine two surrogates between two iterations. By doing this, the online correction procedure can be made very efficient. Numerical experiments confirm that the proposed approach can obtain accurate posterior information with limited number of forward simulations.

READ FULL TEXT

page 9

page 12

page 15

page 16

page 17

research
12/06/2017

Inverse modeling of hydrologic systems with adaptive multi-fidelity Markov chain Monte Carlo simulations

Markov chain Monte Carlo (MCMC) simulation methods are widely used to as...
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
12/06/2017

Inverse modeling of hydrologic systems with adaptive multi-fidelity simulations

Markov chain Monte Carlo (MCMC) simulation methods are widely used to as...
research
07/10/2023

Functional PCA and Deep Neural Networks-based Bayesian Inverse Uncertainty Quantification with Transient Experimental Data

Inverse UQ is the process to inversely quantify the model input uncertai...
research
11/15/2017

Can CNNs Construct Highly Accurate Model Efficiently with Limited Training Samples?

It is well known that metamodel or surrogate modeling techniques have be...
research
10/25/2019

Deep Probabilistic Surrogate Networks for Universal Simulator Approximation

We present a framework for automatically structuring and training fast, ...
research
03/20/2023

Solving High-Dimensional Inverse Problems with Auxiliary Uncertainty via Operator Learning with Limited Data

In complex large-scale systems such as climate, important effects are ca...

Please sign up or login with your details

Forgot password? Click here to reset