paper-with-me

Papers

GAS: A Gaussian Mixture Distribution-Based Adaptive Sampling Method for PINNs

2023-03-28 · Yuling Jiao, Di Li, Xiliang Lu, Jerry Zhijian Yang, Cheng Yuan

With the recent study of deep learning in scientific computation, the Physics-Informed Neural Networks (PINNs) method has drawn widespread attention for solving Partial Differential Equations (PDEs). Compared to traditional methods, PINNs can efficiently handle high-dimensional problems, but the accuracy is relatively low, especially for highly irregular problems. Inspired by the idea of adaptive finite element methods and incremental learning, we propose GAS, a Gaussian mixture distribution-based adaptive sampling method for PINNs. During the training procedure, GAS uses the current residual information to generate a Gaussian mixture distribution for the sampling of additional points, which are then trained together with historical data to speed up the convergence of the loss and achieve higher accuracy. Several numerical simulations on 2D and 10D problems show that GAS is a promising method that achieves state-of-the-art accuracy among deep solvers, while being comparable with traditional numerical solvers.

📄 PDF Abstract BibTeX arXiv:2303.15849

Code (0)

등록된 구현이 없습니다.

Tasks

Incremental Learning

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

A comprehensive study of non-adaptive and residual-based adaptive sampling for physics-informed neural networks

2022-07-21 · Chenxi Wu, Min Zhu, Qinyang Tan, Yadhu Kartha 외

Physics-informed neural networks (PINNs) have shown to be an effective tool for solving forward and inverse problems of partial differential equations (PDEs). PINNs embed the PDEs into the loss of the neural network, and…

Failure-informed adaptive sampling for PINNs, Part II: combining with re-sampling and subset simulation

2023-02-03 · Zhiwei Gao, Tao Tang, Liang Yan, Tao Zhou

This is the second part of our series works on failure-informed adaptive sampling for physic-informed neural networks (FI-PINNs). In our previous work \cite{gao2022failure}, we have presented an adaptive sampling framewo…

Learning Where the Physics Is: Probabilistic Adaptive Sampling for Stiff PDEs

2026-03-06 · Akshay Govind Srinivasan, Balaji Srinivasan arxiv

Modeling stiff partial differential equations (PDEs) with sharp gradients remains a significant challenge for scientific machine learning. While Physics-Informed Neural Networks (PINNs) struggle with spectral bias and sl…

RANG: A Residual-based Adaptive Node Generation Method for Physics-Informed Neural Networks

2022-05-02 · Wei Peng, Weien Zhou, Xiaoya Zhang, Wen Yao 외

Learning solutions of partial differential equations (PDEs) with Physics-Informed Neural Networks (PINNs) is an attractive alternative approach to traditional solvers due to its flexibility and ease of incorporating obse…

Computational Efficiency

DAS-PINNs for high-dimensional partial differential equations: extending deep adaptive sampling to spacetime domains

2026-06-04 · Anshima Singh, David J. Silvester arxiv

Time-dependent high-dimensional partial differential equations (PDEs) with spatially localised and dynamically evolving solutions pose a fundamental challenge for physics-informed neural networks (PINNs), as uniform coll…