Copertina

Quantifying Training Difficulty and Accelerating Convergence in Neural Network-Based PDE Solvers

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Chen, Chuqi, Zhou, Qixuan, Yang, Yahong, Xiang, Yang, Luo, Tao
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Numerical Analysis Machine Learning
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Automatic Differentiation is Essential in Training Neural Networks for Solving Differential Equations
di: Chen, Chuqi, et al.
Pubblicazione: (2024)

SSBE-PINN: A Sobolev Boundary Scheme Boosting Stability and Accuracy in Elliptic/Parabolic PDE Learning
di: Zhou, Qixuan, et al.
Pubblicazione: (2025)

Learn Singularly Perturbed Solutions via Homotopy Dynamics
di: Chen, Chuqi, et al.
Pubblicazione: (2025)

Learning Neural PDE Solvers with Convergence Guarantees
di: Hsieh, Jun-Ting, et al.
Pubblicazione: (2019)

DeepONet for Solving Nonlinear Partial Differential Equations with Physics-Informed Training
di: Yang, Yahong
Pubblicazione: (2024)

Learning Operators through Coefficient Mappings in Fixed Basis Spaces
di: Chen, Chuqi, et al.
Pubblicazione: (2025)

Convergence Guarantees for Gradient-Based Training of Neural PDE Solvers: From Linear to Nonlinear PDEs
di: Zhao, Wei, et al.
Pubblicazione: (2025)

Unisolver: PDE-Conditional Transformers Towards Universal Neural PDE Solvers
di: Zhou, Hang, et al.
Pubblicazione: (2024)

Blending Neural Operators and Relaxation Methods in PDE Numerical Solvers
di: Zhang, Enrui, et al.
Pubblicazione: (2022)

On the Dimension-Free Approximation of Deep Neural Networks for Symmetric Korobov Functions
di: Lu, Yulong, et al.
Pubblicazione: (2025)

Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter
di: Wu, Yuhan, et al.
Pubblicazione: (2026)

Newton Informed Neural Operator for Computing Multiple Solutions of Nonlinear Partials Differential Equations
di: Hao, Wenrui, et al.
Pubblicazione: (2024)

Monte Carlo Neural PDE Solver for Learning PDEs via Probabilistic Representation
di: Zhang, Rui, et al.
Pubblicazione: (2023)

A PDE-based Explanation of Extreme Numerical Sensitivities and Edge of Stability in Training Neural Networks
di: Sun, Yuxin, et al.
Pubblicazione: (2022)

Better Neural PDE Solvers Through Data-Free Mesh Movers
di: Hu, Peiyan, et al.
Pubblicazione: (2023)

Physics-Informed Gaussian Process Regression Generalizes Linear PDE Solvers
di: Pförtner, Marvin, et al.
Pubblicazione: (2022)

A Variational Framework for Residual-Based Adaptivity in Neural PDE Solvers and Operator Learning
di: Toscano, Juan Diego, et al.
Pubblicazione: (2025)

CodePDE: An Inference Framework for LLM-driven PDE Solver Generation
di: Li, Shanda, et al.
Pubblicazione: (2025)

Energy stable neural network for gradient flow equations
di: Wu, Yue, et al.
Pubblicazione: (2023)

Moving Sampling Physics-informed Neural Networks induced by Moving Mesh PDE
di: Yang, Yu, et al.
Pubblicazione: (2023)

PDE Solvers Should Be Local: Fast, Stable Rollouts with Learned Local Stencils
di: Cheng, Chun-Wun, et al.
Pubblicazione: (2025)

Flexible and Efficient Probabilistic PDE Solvers through Gaussian Markov Random Fields
di: Weiland, Tim, et al.
Pubblicazione: (2025)

Mixture-of-Experts Operator Transformer for Large-Scale PDE Pre-Training
di: Wang, Hong, et al.
Pubblicazione: (2025)

Accelerating Conjugate Gradient Solvers for Homogenization Problems with Unitary Neural Operators
di: Herb, Julius, et al.
Pubblicazione: (2025)

Deeper or Wider: A Perspective from Optimal Generalization Error with Sobolev Loss
di: Yang, Yahong, et al.
Pubblicazione: (2024)

DeltaPhi: Physical States Residual Learning for Neural Operators in Data-Limited PDE Solving
di: Yue, Xihang, et al.
Pubblicazione: (2024)

Energy Approach from $\varepsilon$-Graph to Continuum Diffusion Model with Connectivity Functional
di: Yang, Yahong, et al.
Pubblicazione: (2025)

Dual-Balancing for Physics-Informed Neural Networks
di: Zhou, Chenhong, et al.
Pubblicazione: (2025)

$ε$-rank and the Staircase Phenomenon: New Insights into Neural Network Training Dynamics
di: Yang, Jiang, et al.
Pubblicazione: (2024)

End-to-End Mesh Optimization of a Hybrid Deep Learning Black-Box PDE Solver
di: Ma, Shaocong, et al.
Pubblicazione: (2024)

Supervised and Unsupervised Neural Network Solver for First Order Hyperbolic Nonlinear PDEs
di: Baba, Zakaria, et al.
Pubblicazione: (2026)

Graph Neural Regularizers for PDE Inverse Problems
di: Lauga, William, et al.
Pubblicazione: (2025)

Understanding the Difficulty of Solving Cauchy Problems with PINNs
di: Wang, Tao, et al.
Pubblicazione: (2024)

Learning Sparse Approximate Inverse Preconditioners for Conjugate Gradient Solvers on GPUs
di: Yang, Zherui, et al.
Pubblicazione: (2025)

Deep Learning-Enhanced Preconditioning for Efficient Conjugate Gradient Solvers in Large-Scale PDE Systems
di: Li, Rui, et al.
Pubblicazione: (2024)

Latent Neural Operator for Solving Forward and Inverse PDE Problems
di: Wang, Tian, et al.
Pubblicazione: (2024)

Neural Parameter Regression for Explicit Representations of PDE Solution Operators
di: Mundinger, Konrad, et al.
Pubblicazione: (2024)

Deep Neural Networks with General Activations: Super-Convergence in Sobolev Norms
di: Yang, Yahong, et al.
Pubblicazione: (2025)

U-HNO: A U-shaped Hybrid Neural Operator with Sparse-Point Adaptive Routing for Non-stationary PDE Dynamics
di: Ma, Yingzhe, et al.
Pubblicazione: (2026)

Accelerating Legacy Numerical Solvers by Non-intrusive Gradient-based Meta-solving
di: Arisaka, Sohei, et al.
Pubblicazione: (2024)