Cover Image

Stabilizing Physics-Informed Consistency Models via Structure-Preserving Training

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chang, Che-Chia, Dai, Chen-Yang, Lin, Te-Sheng, Lai, Ming-Chih, Lai, Chieh-Hsin
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Numerical Analysis
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

TINNs: Time-Induced Neural Networks for Solving Time-Dependent PDEs
by: Dai, Chen-Yang, et al.
Published: (2026)

A hybrid neural-network and MAC scheme for Stokes interface problems
by: Chang, Che-Chia, et al.
Published: (2023)

Consistency Training with Physical Constraints
by: Chang, Che-Chia, et al.
Published: (2025)

A categorical embedding discontinuity-capturing shallow neural network for anisotropic elliptic interface problems
by: Hu, Wei-Fan, et al.
Published: (2025)

A shallow physics-informed neural network for solving partial differential equations on surfaces
by: Hu, Wei-Fan, et al.
Published: (2022)

Physics-Informed Machine Learning for Two-Phase Moving-Interface and Stefan Problems
by: Chang, Che-Chia, et al.
Published: (2025)

A Unified Weighted-Loss Physics-Informed Neural Network for Boundary Layer Problems in Singularly Perturbed PDEs
by: Hu, Wei-Fan, et al.
Published: (2026)

The Optimal Linear B-splines Approximation via Kolmogorov Superposition Theorem and its Application
by: Lai, Ming-Jun, et al.
Published: (2024)

Non-Asymptotic Stability and Consistency Guarantees for Physics-Informed Neural Networks via Coercive Operator Analysis
by: Katende, Ronald
Published: (2025)

Graph-based Semi-supervised Local Clustering with Few Labeled Nodes
by: Shen, Zhaiming, et al.
Published: (2022)

The Kolmogorov Superposition Theorem can Break the Curse of Dimensionality When Approximating High Dimensional Functions
by: Lai, Ming-Jun, et al.
Published: (2021)

Matrix-Free Stabilized BDF Schemes for Semilinear Parabolic Equations with Unconditional Maximum Bound Principle Preservation and Energy Stability
by: Dai, Haishen, et al.
Published: (2026)

On the Stability and Convergence of Physics Informed Neural Networks
by: Gazoulis, Dimitrios, et al.
Published: (2023)

A Hybrid Discontinuous Galerkin Method with Isogeometric-Planewaves Coupling for Periodic Full-Potential Electronic Structure Calculations
by: Lai, Baowei, et al.
Published: (2026)

DMIS: Dynamic Mesh-based Importance Sampling for Training Physics-Informed Neural Networks
by: Yang, Zijiang, et al.
Published: (2022)

A Singularity Guided Nyström Method for Elastostatics on Two Dimensional Domains with Corners
by: Xie, Baoling, et al.
Published: (2025)

Stabilizing the Consistent Quasidiffusion Method with Linear Prolongation
by: Wang, Dean
Published: (2024)

Stability in Training PINNs for Stiff PDEs: Why Initial Conditions Matter
by: Hao, Baoli, et al.
Published: (2024)

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

On a Modified Random Genetic Drift Model: Derivation and a Structure-Preserving Operator-Splitting Discretization
by: Chen, Chi-An, et al.
Published: (2025)

Maximal Volume Matrix Cross Approximation for Image Compression and Least Squares Solution
by: Allen, Kenneth, et al.
Published: (2023)

A Structure-Preserving Scheme for the Time-Dependent Ginzburg-Landau Model with BCS Gap Coupling
by: Wang, Boyi, et al.
Published: (2026)

Structure-Preserving Operator Learning: Modeling the Collision Operator of Kinetic Equations
by: Lee, Jae Yong, et al.
Published: (2024)

A Structure-Preserving Domain Decomposition Method for Data-Driven Modeling
by: Jiang, Shuai, et al.
Published: (2024)

Mixed Consistent PINNs for Elliptic Obstacle Problems with Stability Analysis
by: Khan, Arbaz, et al.
Published: (2026)

Design-Informed Generative Modelling using Structural Optimization
by: Sarma, Lowhikan Sivanantha, et al.
Published: (2023)

Reducing Training Complexity in Empirical Quadrature-Based Model Reduction via Structured Compression
by: Liljegren-Sailer, Björn
Published: (2025)

LegONet: Plug-and-Play Structure-Preserving Neural Operator Blocks for Compositional PDE Learning
by: Zhang, Jiahao, et al.
Published: (2026)

AutoBalance: An Automatic Balancing Framework for Training Physics-Informed Neural Networks
by: An, Kang, et al.
Published: (2025)

Structure Preserving Polytopal Discontinuous Galerkin Methods for the Numerical Modeling of Neurodegenerative Diseases
by: Corti, Mattia, et al.
Published: (2023)

On the Strong Stability Preserving Property of Runge-Kutta Methods for Hyperbolic Problems
by: Najafian, Mohammad R., et al.
Published: (2026)

Strong Stability Preservation for Stochastic Partial Differential Equations
by: Woodfield, James
Published: (2024)

Structure-Preserving Numerical Methods for Fokker-Planck Equations
by: Bartel, Hanna, et al.
Published: (2024)

Five-Structures Preserving Algorithm for charge dynamics model
by: Sun, Haoran, et al.
Published: (2026)

Structured First-Layer Initialization Pre-Training Techniques to Accelerate Training Process Based on $\varepsilon$-Rank
by: Tang, Tao, et al.
Published: (2025)

Singular Layer Physics-Informed Neural Network Method for Convection-Dominated Boundary Layer Problems in Two Dimensions
by: Gie, Gung-Min, et al.
Published: (2023)

A Structure-Preserving Numerical Method for Harmonic Maps Between High-genus Surfaces
by: Zhu, Zhipeng, et al.
Published: (2025)

Structure-Preserving Transfer of Grad-Shafranov Equilibria to Magnetohydrodynamic Solvers
by: Zhang, Rushan, et al.
Published: (2025)

Structure-Preserving and Pressure-Robust PINNs for Incompressible Oseen Problems
by: Mishra, Shiv, et al.
Published: (2026)

Structure-Preserving Neural Ordinary Differential Equations for Stiff Systems
by: Loya, Allen Alvarez, et al.
Published: (2025)