paper-with-me

Papers

A Method for Computing Inverse Parametric PDE Problems with Random-Weight Neural Networks

2022-10-09 · Suchuan Dong, Yiran Wang

We present a method for computing the inverse parameters and the solution field to inverse parametric PDEs based on randomized neural networks. This extends the local extreme learning machine technique originally developed for forward PDEs to inverse problems. We develop three algorithms for training the neural network to solve the inverse PDE problem. The first algorithm (NLLSQ) determines the inverse parameters and the trainable network parameters all together by the nonlinear least squares method with perturbations (NLLSQ-perturb). The second algorithm (VarPro-F1) eliminates the inverse parameters from the overall problem by variable projection to attain a reduced problem about the trainable network parameters only. It solves the reduced problem first by the NLLSQ-perturb algorithm for the trainable network parameters, and then computes the inverse parameters by the linear least squares method. The third algorithm (VarPro-F2) eliminates the trainable network parameters from the overall problem by variable projection to attain a reduced problem about the inverse parameters only. It solves the reduced problem for the inverse parameters first, and then computes the trainable network parameters afterwards. VarPro-F1 and VarPro-F2 are reciprocal to each other in a sense. The presented method produces accurate results for inverse PDE problems, as shown by the numerical examples herein. For noise-free data, the errors for the inverse parameters and the solution field decrease exponentially as the number of collocation points or the number of trainable network parameters increases, and can reach a level close to the machine accuracy. For noisy data, the accuracy degrades compared with the case of noise-free data, but the method remains quite accurate. The presented method has been compared with the physics-informed neural network method.

📄 PDF Abstract BibTeX arXiv:2210.04338

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Fully probabilistic deep models for forward and inverse problems in parametric PDEs

2022-08-09 · Arnaud Vadeboncoeur, Ömer Deniz Akyildiz, Ieva Kazlauskaite, Mark Girolami 외

We introduce a physics-driven deep latent variable model (PDDLVM) to learn simultaneously parameter-to-solution (forward) and solution-to-parameter (inverse) maps of parametric partial differential equations (PDEs). Our …

Variational Inference

Solving Non-parametric Inverse Problem in Continuous Markov Random Field using Loopy Belief Propagation

2017-03-28 · Muneki Yasuda, Shun Kataoka

In this paper, we address the inverse problem, or the statistical machine learning problem, in Markov random fields with a non-parametric pair-wise energy function with continuous variables. The inverse problem is formul…

Form

Multivariate root-n-consistent smoothing parameter free matching estimators and estimators of inverse density weighted expectations

2024-07-11 · Hajo Holzmann, Alexander Meister

Expected values weighted by the inverse of a multivariate density or, equivalently, Lebesgue integrals of regression functions with multivariate regressors occur in various areas of applications, including estimating ave…

regression

Random Grid Neural Processes for Parametric Partial Differential Equations

2023-01-26 · Arnaud Vadeboncoeur, Ieva Kazlauskaite, Yanni Papandreou, Fehmi Cirak 외

We introduce a new class of spatially stochastic physics and data informed deep latent models for parametric partial differential equations (PDEs) which operate through scalable variational neural processes. We achieve t…

Randomized neural operator for parametric PDEs with fast training and conformal uncertainty quantification

2026-06-28 · Zirui Deng, Jingbo Sun, Deyu Meng, Fei Wang arxiv

Repeatedly solving parametric PDEs is essential for uncertainty quantification, design optimization and inverse problems, but conventional neural operators require expensive non-convex training. We introduce PCA--RaNN, a…

Dimensionality Reduction