Copertina

Kronecker-Factored Approximate Curvature for Physics-Informed Neural Networks

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Dangel, Felix, Müller, Johannes, Zeinhofer, Marius
Natura:	Preprint
Pubblicazione:	2024
Soggetti:	Machine Learning Computational Physics
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Kronecker-factored Approximate Curvature (KFAC) From Scratch
di: Dangel, Felix, et al.
Pubblicazione: (2025)

Collapsing Taylor Mode Automatic Differentiation
di: Dangel, Felix, et al.
Pubblicazione: (2025)

Improving Energy Natural Gradient Descent through Woodbury, Momentum, and Randomization
di: Guzmán-Cordero, Andrés, et al.
Pubblicazione: (2025)

Curvature-Aware Optimization for High-Accuracy Physics-Informed Neural Networks
di: Jnini, Anas, et al.
Pubblicazione: (2026)

Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures
di: Eschenhagen, Runa, et al.
Pubblicazione: (2023)

Functional Neural Wavefunction Optimization
di: Armegioiu, Victor, et al.
Pubblicazione: (2025)

Convolutions and More as Einsum: A Tensor Network Perspective with Advances for Second-Order Methods
di: Dangel, Felix
Pubblicazione: (2023)

Gauss-Newton Natural Gradient Descent for Physics-Informed Computational Fluid Dynamics
di: Jnini, Anas, et al.
Pubblicazione: (2024)

Statistical Learning Analysis of Physics-Informed Neural Networks
di: Barajas-Solano, David A.
Pubblicazione: (2026)

Evidential Physics-Informed Neural Networks for Scientific Discovery
di: Tan, Hai Siong, et al.
Pubblicazione: (2025)

On the Role of Consistency Between Physics and Data in Physics-Informed Neural Networks
di: Becerra-Zuniga, Nicolás, et al.
Pubblicazione: (2026)

Error Analysis and Numerical Algorithm for PDE Approximation with Hidden-Layer Concatenated Physics Informed Neural Networks
di: Qian, Yianxia, et al.
Pubblicazione: (2024)

Quantum Noise Tomography with Physics-Informed Neural Networks
di: Sulc, Antonin
Pubblicazione: (2025)

Evidential Physics-Informed Neural Networks
di: Tan, Hai Siong, et al.
Pubblicazione: (2025)

On the Disconnect Between Theory and Practice of Neural Networks: Limits of the NTK Perspective
di: Wenger, Jonathan, et al.
Pubblicazione: (2023)

Physics-Informed Neural Networks for Solving Derivative-Constrained PDEs
di: Hoshisashi, Kentaro, et al.
Pubblicazione: (2026)

PINGS: Physics-Informed Neural Network for Fast Generative Sampling
di: Prasha, Achmad Ardani, et al.
Pubblicazione: (2025)

Exact Enforcement of Temporal Continuity in Sequential Physics-Informed Neural Networks
di: Roy, Pratanu, et al.
Pubblicazione: (2024)

Physics-Informed Neural Networks with Fourier Features and Attention-Driven Decoding
di: Arni, Rohan, et al.
Pubblicazione: (2025)

DiffGrad for Physics-Informed Neural Networks
di: Rahman, Jamshaid Ul, et al.
Pubblicazione: (2024)

Bayesian Reasoning for Physics Informed Neural Networks
di: Graczyk, Krzysztof M., et al.
Pubblicazione: (2023)

A New Way: Kronecker-Factored Approximate Curvature Deep Hedging and its Benefits
di: Enkhbayar, Tsogt-Ochir
Pubblicazione: (2024)

Response Estimation and System Identification of Dynamical Systems via Physics-Informed Neural Networks
di: Haywood-Alexander, Marcus, et al.
Pubblicazione: (2024)

Dynamical Measure Transport and Neural PDE Solvers for Sampling
di: Sun, Jingtong, et al.
Pubblicazione: (2024)

Generalized Lie Symmetries in Physics-Informed Neural Operators
di: Wang, Amy Xiang, et al.
Pubblicazione: (2025)

Physics-Informed Neural Solvers for Periodic Quantum Eigenproblems
di: Mian, Haaris
Pubblicazione: (2025)

Taper-based scattering formulation of the Helmholtz equation to improve the training process of Physics-Informed Neural Networks
di: Dörfler, W., et al.
Pubblicazione: (2024)

PINN-FEM: A Hybrid Approach for Enforcing Dirichlet Boundary Conditions in Physics-Informed Neural Networks
di: Sobh, Nahil, et al.
Pubblicazione: (2025)

Leveraging Influence Functions for Resampling Data in Physics-Informed Neural Networks
di: Naujoks, Jonas R., et al.
Pubblicazione: (2025)

Examining the robustness of Physics-Informed Neural Networks to noise for Inverse Problems
di: Jekic, Aleksandra, et al.
Pubblicazione: (2025)

Dataless Weight Disentanglement in Task Arithmetic via Kronecker-Factored Approximate Curvature
di: Porrello, Angelo, et al.
Pubblicazione: (2026)

Residual Attention Physics-Informed Neural Networks for Robust Multiphysics Simulation of Steady-State Electrothermal Energy Systems
di: Zhou, Yuqing, et al.
Pubblicazione: (2026)

EquiNO: A Physics-Informed Neural Operator for Multiscale Simulations
di: Eivazi, Hamidreza, et al.
Pubblicazione: (2025)

PINNfluence: Influence Functions for Physics-Informed Neural Networks
di: Naujoks, Jonas R., et al.
Pubblicazione: (2024)

Energy Dissipation Preserving Physics Informed Neural Network for Allen-Cahn Equations
di: Kütük, Mustafa, et al.
Pubblicazione: (2024)

Physics-Informed Neural Network based Damage Identification for Truss Railroad Bridges
di: Shajihan, Althaf, et al.
Pubblicazione: (2025)

Quantum-Classical Physics-Informed Neural Networks for Solving Reservoir Seepage Equations
di: Rao, Xiang, et al.
Pubblicazione: (2025)

Training Deep Physics-Informed Kolmogorov-Arnold Networks
di: Rigas, Spyros, et al.
Pubblicazione: (2025)

Finite Basis Physics-Informed Neural Networks (FBPINNs): a scalable domain decomposition approach for solving differential equations
di: Moseley, Ben, et al.
Pubblicazione: (2021)

Self-Adaptive Physics-Informed Quantum Machine Learning for Solving Differential Equations
di: Setty, Abhishek, et al.
Pubblicazione: (2023)