When and why PINNs fail to train: A neural tangent kernel perspective

28 July 2020

Papers citing "When and why PINNs fail to train: A neural tangent kernel perspective"

50 / 336 papers shown

Title
Feature-adjacent multi-fidelity physics-informed machine learning for partial differential equations Wenqian Chen P. Stinis OOD AI4CE 27 7 0 21 Mar 2023
Controlled Descent Training Viktor Andersson B. Varga Vincent Szolnoky Andreas Syrén Rebecka Jörnsten Balázs Kulcsár 33 1 0 16 Mar 2023
On the uncertainty analysis of the data-enabled physics-informed neural network for solving neutron diffusion eigenvalue problem Yu Yang Helin Gong Qihong Yang Yangtao Deng Qiaolin He Shiquan Zhang DiffM 38 9 0 15 Mar 2023
Error convergence and engineering-guided hyperparameter search of PINNs: towards optimized I-FENN performance Panos Pantidis Habiba Eldababy Christopher Miguel Tagle M. Mobasher 27 20 0 03 Mar 2023
Physics-Informed Deep Learning For Traffic State Estimation: A Survey and the Outlook Xuan Di Rongye Shi Zhaobin Mo Yongjie Fu PINN AI4TS AI4CE 24 28 0 03 Mar 2023
Implicit Stochastic Gradient Descent for Training Physics-informed Neural Networks Ye Li Songcan Chen Shengyi Huang PINN 12 1 0 03 Mar 2023
Physics-informed neural networks for solving forward and inverse problems in complex beam systems Taniya Kapoor Hongrui Wang A. Núñez R. Dollevoet AI4CE PINN 21 46 0 02 Mar 2023
A unified scalable framework for causal sweeping strategies for Physics-Informed Neural Networks (PINNs) and their temporal decompositions Michael Penwarden Ameya Dilip Jagtap Shandian Zhe George Karniadakis Robert M. Kirby PINN AI4CE 16 57 0 28 Feb 2023
Achieving High Accuracy with PINNs via Energy Natural Gradients Johannes Müller Marius Zeinhofer 11 4 0 25 Feb 2023
Ensemble learning for Physics Informed Neural Networks: a Gradient Boosting approach Zhiwei Fang Sifan Wang P. Perdikaris PINN AI4CE 11 5 0 25 Feb 2023
On the Limitations of Physics-informed Deep Learning: Illustrations Using First Order Hyperbolic Conservation Law-based Traffic Flow Models Archie J. Huang S. Agarwal AI4CE PINN 16 25 0 23 Feb 2023
PIFON-EPT: MR-Based Electrical Property Tomography Using Physics-Informed Fourier Networks Xinling Yu José E. C. Serrallés Ilias I. Giannakopoulos Z. Liu Luca Daniel R. Lattanzi Zheng-Wei Zhang 14 10 0 23 Feb 2023
Learning Physical Models that Can Respect Conservation Laws Derek Hansen Danielle C. Maddix S. Alizadeh Gaurav Gupta Michael W. Mahoney AI4CE 34 42 0 21 Feb 2023
h-analysis and data-parallel physics-informed neural networks Paul Escapil-Inchauspé G. A. Ruz PINN AI4CE 27 2 0 17 Feb 2023
On the Generalization of PINNs outside the training domain and the Hyperparameters influencing it Andrea Bonfanti Roberto Santana M. Ellero Babak Gholami AI4CE PINN 35 3 0 15 Feb 2023
Monte Carlo Neural PDE Solver for Learning PDEs via Probabilistic Representation Rui Zhang Qi Meng Rongchan Zhu Yue Wang Wenlei Shi Shihua Zhang Zhi-Ming Ma Tie-Yan Liu DiffM AI4CE 44 4 0 10 Feb 2023
Failure-informed adaptive sampling for PINNs, Part II: combining with re-sampling and subset simulation Zhi-Hao Gao Tao Tang Liang Yan Tao Zhou 29 18 0 03 Feb 2023
Temporal Consistency Loss for Physics-Informed Neural Networks Sukirt Thakur M. Raissi H. Mitra A. Ardekani PINN 14 10 0 30 Jan 2023
Solving High-Dimensional PDEs with Latent Spectral Models Haixu Wu Tengge Hu Huakun Luo Jianmin Wang Mingsheng Long AI4CE 57 37 0 30 Jan 2023
BINN: A deep learning approach for computational mechanics problems based on boundary integral equations Jia Sun Yinghua Liu Yizheng Wang Z. Yao Xiao-ping Zheng PINN AI4CE 17 23 0 11 Jan 2023
Deep learning for full-field ultrasonic characterization Yang Xu Fatemeh Pourahmadian Jian Song Congli Wang AI4CE 29 4 0 06 Jan 2023
Characteristics-Informed Neural Networks for Forward and Inverse Hyperbolic Problems U. Braga-Neto PINN AI4CE 25 8 0 28 Dec 2022
Physics-Informed Neural Networks for Material Model Calibration from Full-Field Displacement Data D. Anton Henning Wessels AI4CE 28 7 0 15 Dec 2022
Harmonic (Quantum) Neural Networks Atiyo Ghosh Antonio A. Gentile M. Dagrada Chul Lee S. Kim Hyukgeun Cha Yunjun Choi Brad Kim J. Kye V. Elfving AI4CE 21 1 0 14 Dec 2022
Deep Learning Methods for Partial Differential Equations and Related Parameter Identification Problems Derick Nganyu Tanyu Jianfeng Ning Tom Freudenberg Nick Heilenkötter A. Rademacher U. Iben Peter Maass AI4CE 18 34 0 06 Dec 2022
Bayesian Physics Informed Neural Networks for Data Assimilation and Spatio-Temporal Modelling of Wildfires J. Dabrowski D. Pagendam J. Hilton Conrad Sanderson Dan MacKinlay C. Huston Andrew Bolt Petra Kuhnert PINN 25 17 0 02 Dec 2022
On the Compatibility between Neural Networks and Partial Differential Equations for Physics-informed Learning Kuangdai Leng Jeyan Thiyagalingam PINN 24 2 0 01 Dec 2022
Utilising physics-guided deep learning to overcome data scarcity Jinshuai Bai Laith Alzubaidi Qingxia Wang E. Kuhl Bennamoun Yuantong T. Gu PINN AI4CE 26 3 0 24 Nov 2022
Neural tangent kernel analysis of PINN for advection-diffusion equation M. Saadat B. Gjorgiev L. Das G. Sansavini 25 0 0 21 Nov 2022
Physics-Informed Koopman Network Yuying Liu A. Sholokhov Hassan Mansour S. Nabi AI4CE 23 3 0 17 Nov 2022
SVD-PINNs: Transfer Learning of Physics-Informed Neural Networks via Singular Value Decomposition Yihang Gao Ka Chun Cheung Michael K. Ng 25 15 0 16 Nov 2022
Physics-Informed Machine Learning: A Survey on Problems, Methods and Applications Zhongkai Hao Songming Liu Yichi Zhang Chengyang Ying Yao Feng Hang Su Jun Zhu PINN AI4CE 23 89 0 15 Nov 2022
A Deep Double Ritz Method (D $^2$ RM) for solving Partial Differential Equations using Neural Networks C. Uriarte David Pardo I. Muga J. Muñoz‐Matute 29 17 0 07 Nov 2022
Neural PDE Solvers for Irregular Domains Biswajit Khara Ethan Herron Zhanhong Jiang Aditya Balu Chih-Hsuan Yang ... Anushrut Jignasu S. Sarkar C. Hegde A. Krishnamurthy Baskar Ganapathysubramanian AI4CE 17 7 0 07 Nov 2022
Partial Differential Equations Meet Deep Neural Networks: A Survey Shudong Huang Wentao Feng Chenwei Tang Jiancheng Lv AI4CE AIMat 24 17 0 27 Oct 2022
Neuro-symbolic partial differential equation solver Pouria A. Mistani Samira Pakravan Rajesh Ilango S. Choudhry Frédéric Gibou 26 1 0 25 Oct 2022
Less Emphasis on Difficult Layer Regions: Curriculum Learning for Singularly Perturbed Convection-Diffusion-Reaction Problems Yufeng Wang Cong Xu Min Yang Jin Zhang 9 4 0 23 Oct 2022
Meta Learning of Interface Conditions for Multi-Domain Physics-Informed Neural Networks Shibo Li Michael Penwarden Yiming Xu Conor Tillinghast Akil Narayan Robert M. Kirby Shandian Zhe AI4CE 14 4 0 23 Oct 2022
An unsupervised latent/output physics-informed convolutional-LSTM network for solving partial differential equations using peridynamic differential operator A. Mavi A. Bekar E. Haghighat E. Madenci 57 28 0 21 Oct 2022
Tunable Complexity Benchmarks for Evaluating Physics-Informed Neural Networks on Coupled Ordinary Differential Equations Alexander New B. Eng A. Timm A. Gearhart 12 4 0 14 Oct 2022
PDEBENCH: An Extensive Benchmark for Scientific Machine Learning M. Takamoto T. Praditia Raphael Leiteritz Dan MacKinlay Francesco Alesiani Dirk Pflüger Mathias Niepert AI4CE 22 201 0 13 Oct 2022
A Unified Hard-Constraint Framework for Solving Geometrically Complex PDEs Songming Liu Zhongkai Hao Chengyang Ying Hang Su Jun Zhu Ze Cheng AI4CE 10 17 0 06 Oct 2022
Failure-informed adaptive sampling for PINNs Zhiwei Gao Liang Yan Tao Zhou 16 77 0 01 Oct 2022
Joint Embedding Self-Supervised Learning in the Kernel Regime B. Kiani Randall Balestriero Yubei Chen S. Lloyd Yann LeCun SSL 41 13 0 29 Sep 2022
Scaling transformation of the multimode nonlinear Schrödinger equation for physics-informed neural networks I. Chuprov D. Efremenko Jiexing Gao P. Anisimov V. Zemlyakov 16 0 0 29 Sep 2022
Approximating the full-field temperature evolution in 3D electronic systems from randomized "Minecraft" systems Monika Stipsitz H. Sanchis-Alepuz AI4CE 13 2 0 21 Sep 2022
Residual-Quantile Adjustment for Adaptive Training of Physics-informed Neural Network Jiayue Han Zhiqiang Cai Zhiyou Wu Xiang Zhou 42 7 0 09 Sep 2022
Inverse modeling of nonisothermal multiphase poromechanics using physics-informed neural networks Daniel Amini E. Haghighat R. Juanes PINN AI4CE 19 32 0 07 Sep 2022
Solving Elliptic Problems with Singular Sources using Singularity Splitting Deep Ritz Method Tianhao Hu Bangti Jin Zhi Zhou 23 6 0 07 Sep 2022
Learning Differential Operators for Interpretable Time Series Modeling Yingtao Luo Chang Xu Yang Liu Weiqing Liu Shun Zheng Jiang Bian AI4TS 37 8 0 03 Sep 2022