Challenges in Training PINNs: A Loss Landscape Perspective

Challenges in Training PINNs: A Loss Landscape Perspective

2 February 2024

Zachary Frangella

Madeleine Udell

Papers citing "Challenges in Training PINNs: A Loss Landscape Perspective"

19 / 19 papers shown

Title
Physics-informed neural network estimation of active material properties in time-dependent cardiac biomechanical models Matthias Höfler Francesco Regazzoni S. Pagani Elias Karabelas Christoph M. Augustin Gundolf Haase Gernot Plank Federica Caforio 17 0 0 06 May 2025
Integration Matters for Learning PDEs with Backwards SDEs Sungje Park Stephen Tu PINN 50 0 0 02 May 2025
PaperBench: Evaluating AI's Ability to Replicate AI Research Giulio Starace Oliver Jaffe Dane Sherburn James Aung Jun Shern Chan ... Benjamin Kinsella Wyatt Thompson Johannes Heidecke Amelia Glaese Tejal Patwardhan ALM ELM 785 6 0 02 Apr 2025
MultiPDENet: PDE-embedded Learning with Multi-time-stepping for Accelerated Flow Simulation Qi Wang Yuan Mi H. Wang Yi Zhang Ruizhi Chengze Hongsheng Liu J. Wen Hao Sun AI4CE 38 0 0 28 Jan 2025
Enhanced physics-informed neural networks (PINNs) for high-order power grid dynamics Vineet Jagadeesan Nair PINN 38 0 0 10 Oct 2024
Fast Training of Sinusoidal Neural Fields via Scaling Initialization Taesun Yeom Sangyoon Lee Jaeho Lee 51 2 0 07 Oct 2024
On the expressiveness and spectral bias of KANs Yixuan Wang Jonathan W. Siegel Ziming Liu Thomas Y. Hou 32 9 0 02 Oct 2024
Physics-informed kernel learning Nathan Doumèche Francis Bach Gérard Biau Claire Boyer PINN 29 2 0 20 Sep 2024
Beyond Closure Models: Learning Chaotic-Systems via Physics-Informed Neural Operators Chuwei Wang Julius Berner Zongyi Li Di Zhou Jiayun Wang Jane Bae Anima Anandkumar AI4CE 28 1 0 09 Aug 2024
A finite element-based physics-informed operator learning framework for spatiotemporal partial differential equations on arbitrary domains Yusuke Yamazaki Ali Harandi Mayu Muramatsu A. Viardin Markus Apel T. Brepols Stefanie Reese Shahed Rezaei AI4CE 26 12 0 21 May 2024
Finite Basis Physics-Informed Neural Networks (FBPINNs): a scalable domain decomposition approach for solving differential equations Benjamin Moseley Andrew Markham T. Nissen‐Meyer PINN 37 207 0 16 Jul 2021
Efficient training of physics-informed neural networks via importance sampling M. A. Nabian R. J. Gladstone Hadi Meidani DiffM PINN 69 220 0 26 Apr 2021
Physics-informed neural networks with hard constraints for inverse design Lu Lu R. Pestourie Wenjie Yao Zhicheng Wang F. Verdugo Steven G. Johnson PINN 39 489 0 09 Feb 2021
On the eigenvector bias of Fourier feature networks: From regression to solving multi-scale PDEs with physics-informed neural networks Sifan Wang Hanwen Wang P. Perdikaris 131 437 0 18 Dec 2020
Fourier Neural Operator for Parametric Partial Differential Equations Zong-Yi Li Nikola B. Kovachki Kamyar Azizzadenesheli Burigede Liu K. Bhattacharya Andrew M. Stuart Anima Anandkumar AI4CE 203 2,272 0 18 Oct 2020
hp-VPINNs: Variational Physics-Informed Neural Networks With Domain Decomposition E. Kharazmi Zhongqiang Zhang George Karniadakis 117 506 0 11 Mar 2020
A Simple Convergence Proof of Adam and Adagrad Alexandre Défossez Léon Bottou Francis R. Bach Nicolas Usunier 56 143 0 05 Mar 2020
Linear Convergence of Gradient and Proximal-Gradient Methods Under the Polyak-Łojasiewicz Condition Hamed Karimi J. Nutini Mark W. Schmidt 119 1,194 0 16 Aug 2016
Sharp analysis of low-rank kernel matrix approximations Francis R. Bach 75 278 0 09 Aug 2012