Publications

2024

Bridging Operator Learning and Conditioned Neural Fields: A Unifying Perspective
Sifan Wang, Jacob H Seidman, Shyam Sankaran, Hanwen Wang, George J. Pappas, Paris Perdikaris)
arXiv preprint arXiv:2405.13998 (2024)
[Paper] [Code]
PirateNets: Physics-informed Deep Learning with Residual Adaptive Networks
Sifan Wang, Bowen Li, Yuhan Chen, Paris Perdikaris
arXiv preprint arXiv:2402.00326 (2024)
[Paper] [Code]

An Expert’s Guide to Training Physics-Informed Neural Networks
Sifan Wang, Shyam Sankaran, Hanwen Wang, Paris Perdikaris
arXiv preprint arXiv:2308.08468 (2023)
[Paper] [Code]
A Dive into Spectral Inference Networks: Improved Algorithms for Self-Supervised Learning of Continuous Spectral Representations
Jin Wu, Sifan Wang, Paris Perdikaris
Applied Mathematics and Mechanics 44, no. 7 (2023): 1199-1224
[Paper]
PPDONet: Deep Operator Networks for Fast Prediction of Steady-state Solutions in Disk–Planet Systems
Shunyuan Mao, Ruobing Dong, Lu Lu, Kwang Moo Yi, Sifan Wang, and Paris Perdikaris
The Astrophysical Journal Letters 950, no. 2 (2023): L12
[Paper] [Code]
Mitigating Propagation Failures in Physics-informed Neural Networks Using Retain-Resample-Release (R3) Sampling
Daw, Arka, Jie Bu, Sifan Wang, Paris Perdikaris, and Anuj Karpatne
International Conference on Machine Learning (ICML) 2023
[Paper] [Code]
Long-Time Integration of Parametric Evolution Equations with Physics-Informed DeepONets
Sifan Wang, Paris Perdikaris
Journal of Computational Physics 475 (2023): 111855
[Paper] [Code]

Random Weight Factorization Improves the Training of Continuous Neural Representations
Sifan Wang, Hanwen Wang, Jacob H Seidman, Paris Perdikaris
arXiv preprint arXiv:2210.01274 (2022)
[Paper]
Improved Architectures and Training Algorithms for Deep Operator Networks
Sifan Wang, Hanwen Wang, Paris Perdikaris
Journal of Scientific Computing 92, no. 2 (2022): 35
[Paper] [Code]
Respecting Causality is All You Need for Training Physics-Informed Neural Networks
Sifan Wang, Shyam Sankaran, Paris Perdikaris
arXiv preprint arXiv:2203.07404 (2022)
[Paper] [Code]
Adaptive Training Strategies for Physics-Informed Neural Networks
Sifan Wang, Paris Perdikaris
In Knowledge Guided Machine Learning, pp. 133-160. Chapman and Hall/CRC, 2022
[Paper]
When and Why PINNs Fail to Train: A Neural Tangent Kernel Perspective
Sifan Wang, Xinling Yu, Paris Perdikaris
Journal of Computational Physics 449 (2022): 110768
[Paper] [Code]

Physics-Informed Machine Learning
George Em Karniadakis, Ioannis G Kevrekidis, Lu Lu, Paris Perdikaris, Sifan Wang, Liu Yang
Nature Reviews Physics 3, no. 6 (2021): 422-440.
[Paper]
Physics-Informed Neural Networks for Heat Transfer Problems
Shengze Cai, Zhicheng Wang, Sifan Wang, Paris Perdikaris, George Em Karniadakis
Journal of Heat Transfer 143, no. 6 (2021): 060801
[Paper]
Fast PDE-Constrained Optimization via Self-Supervised Operator Learning
Sifan Wang, Mohamed Aziz Bhouri, Paris Perdikaris
arXiv preprint arXiv:2110.13297 (2021)
[Paper]
Learning the Solution Operator of Parametric Partial Differential Equations with Physics-Informed DeepONets
Sifan Wang, Hanwen Wang, Paris Perdikaris
Science advances 7, no. 40 (2021): eabi8605
[Paper] [Code]
On the Eigenvector Bias of Fourier Feature Networks: From Regression to Solving Multi-Scale PDEs with Physics-Informed Neural Networks
Sifan Wang, Hanwen Wang, Paris Perdikaris
Computer Methods in Applied Mechanics and Engineering 384 (2021): 113938
[Paper] [Code]
Deep Learning of Free Boundary and Stefan Problems
Sifan Wang, Paris Perdikaris
Journal of Computational Physics 428 (2021): 109914
[Paper] [Code]
Understanding and Mitigating Gradient Flow Pathologies in Physics-Informed Neural Networks
Sifan Wang, Yujun Teng, Paris Perdikaris
SIAM Journal on Scientific Computing 43, no. 5 (2021): A3055-A3081
[Paper] [Code]