Copertina

Unified theoretical guarantees for stability, consistency, and convergence in neural PDE solvers from non-IID data to physics-informed networks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autore principale:	Katende, Ronald
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Numerical Analysis
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Decentralized Neural Networks for Robust and Scalable Eigenvalue Computation
di: Katende, Ronald
Pubblicazione: (2024)

Structured Variational $D$-Decomposition for Accurate and Stable Low-Rank Approximation
di: Katende, Ronald
Pubblicazione: (2025)

Causal Operator Discovery in Partial Differential Equations via Counterfactual Physics-Informed Neural Networks
di: Katende, Ronald
Pubblicazione: (2025)

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

Adaptive Error-Bounded Hierarchical Matrices for Efficient Neural Network Compression
di: Mango, John, et al.
Pubblicazione: (2024)

KD-PINN: Knowledge-Distilled PINNs for ultra-low-latency real-time neural PDE solvers
di: Bounja, Karim, et al.
Pubblicazione: (2025)

A Frobenius-Optimal Projection for Enforcing Linear Conservation in Learned Dynamical Models
di: Mango, John M., et al.
Pubblicazione: (2025)

Pseudo-differential-enhanced physics-informed neural networks
di: Gracyk, Andrew
Pubblicazione: (2026)

Exact and approximate error bounds for physics-informed neural networks
di: Chantada, Augusto T., et al.
Pubblicazione: (2024)

BO-SA-PINNs: Self-adaptive physics-informed neural networks based on Bayesian optimization for automatically designing PDE solvers
di: Zhang, Rui, et al.
Pubblicazione: (2025)

Physics-informed neural networks for operator equations with stochastic data
di: Escapil-Inchauspé, Paul, et al.
Pubblicazione: (2022)

Domain decomposition architectures and Gauss-Newton training for physics-informed neural networks
di: Heinlein, Alexander, et al.
Pubblicazione: (2025)

Certified machine learning: A posteriori error estimation for physics-informed neural networks
di: Hillebrecht, Birgit, et al.
Pubblicazione: (2022)

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

An extended physics informed neural network for preliminary analysis of parametric optimal control problems
di: Demo, Nicola, et al.
Pubblicazione: (2021)

Optimal time sampling in physics-informed neural networks
di: Turinici, Gabriel
Pubblicazione: (2024)

Long-term simulation of physical and mechanical behaviors using curriculum-transfer-learning based physics-informed neural networks
di: Guo, Yuan, et al.
Pubblicazione: (2025)

A decomposition-based robust training of physics-informed neural networks for nearly incompressible linear elasticity
di: Dick, Josef, et al.
Pubblicazione: (2025)

Random test functions, $H^{-1}$ norm equivalence, and stochastic variational physics-informed neural networks
di: Marcondes, Diego
Pubblicazione: (2026)

Fixed-budget online adaptive learning for physics-informed neural networks. Towards parameterized problem inference
di: Nguyen, Thi Nguyen Khoa, et al.
Pubblicazione: (2022)

Cell-induced densification and tether formation in fibrous extracellular matrices with biomimetic physics-informed neural networks
di: Lin, Anci, et al.
Pubblicazione: (2026)

Symmetry group based domain decomposition to enhance physics-informed neural networks for solving partial differential equations
di: Liu, Ye, et al.
Pubblicazione: (2024)

Core-Conditioned Regularized Matrix Tri-Factorization for High-Dimensional Structured Systems
di: Katende, Ronald
Pubblicazione: (2024)

A Nonlinear Generalization of the Bauer-Fike Theorem and Novel Iterative Methods for Solving Nonlinear Eigenvalue Problems
di: Katende, Ronald
Pubblicazione: (2024)

Numerical analysis of physics-informed neural networks and related models in physics-informed machine learning
di: De Ryck, Tim, et al.
Pubblicazione: (2024)

Multi-Fidelity Delayed Acceptance: hierarchical MCMC sampling for Bayesian inverse problems combining multiple solvers through deep neural networks
di: Zacchei, Filippo, et al.
Pubblicazione: (2025)

A physics-informed neural network framework for modeling obstacle-related equations
di: Bahja, Hamid El, et al.
Pubblicazione: (2023)

Numerical PDE solvers outperform neural PDE solvers
di: Chatain, Patrick, et al.
Pubblicazione: (2025)

RGNMR: A Gauss-Newton method for robust matrix completion with theoretical guarantees
di: Laufer, Eilon Vaknin, et al.
Pubblicazione: (2025)

One-shot acceleration of transient PDE solvers via online-learned preconditioners
di: Khodak, Mikhail, et al.
Pubblicazione: (2025)

A fast neural hybrid Newton solver adapted to implicit methods for nonlinear dynamics
di: Jin, Tianyu, et al.
Pubblicazione: (2024)

VS-PINN: A fast and efficient training of physics-informed neural networks using variable-scaling methods for solving PDEs with stiff behavior
di: Ko, Seungchan, et al.
Pubblicazione: (2024)

Rational-WENO: A lightweight, physically-consistent three-point weighted essentially non-oscillatory scheme
di: Shahane, Shantanu, et al.
Pubblicazione: (2024)

Kolmogorov Arnold Informed neural network: A physics-informed deep learning framework for solving forward and inverse problems based on Kolmogorov Arnold Networks
di: Wang, Yizheng, et al.
Pubblicazione: (2024)

Astral: training physics-informed neural networks with error majorants
di: Fanaskov, Vladimir, et al.
Pubblicazione: (2024)

Improving the accuracy of physics-informed neural networks via last-layer retraining
di: Qadeer, Saad, et al.
Pubblicazione: (2026)

Flexible SE(2) graph neural networks with applications to PDE surrogates
di: Bånkestad, Maria, et al.
Pubblicazione: (2024)

Physics-informed neural networks (PINNs) for numerical model error approximation and superresolution
di: Zhuang, Bozhou, et al.
Pubblicazione: (2024)

Fast training of accurate physics-informed neural networks without gradient descent
di: Datar, Chinmay, et al.
Pubblicazione: (2024)

Convergence of physics-informed neural networks modeling time-harmonic wave fields
di: Schoder, Stefan, et al.
Pubblicazione: (2025)