Cover Image

The Vanishing Gradient Problem for Stiff Neural Differential Equations

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fronk, Colby, Petzold, Linda
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Numerical Analysis Systems and Control
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Training Stiff Neural Ordinary Differential Equations with Explicit Exponential Integration Methods
by: Fronk, Colby, et al.
Published: (2024)

Performance Evaluation of Single-step Explicit Exponential Integration Methods on Stiff Ordinary Differential Equations
by: Fronk, Colby, et al.
Published: (2024)

Training Stiff Neural Ordinary Differential Equations with Implicit Single-Step Methods
by: Fronk, Colby, et al.
Published: (2024)

Error Bounds for Physics-Informed Neural Networks in Fokker-Planck PDEs
by: Kong, Chun-Wei, et al.
Published: (2024)

Monte Carlo-Type Neural Operator for Differential Equations
by: Choutri, Salah Eddine, et al.
Published: (2025)

A Single-Loop Gradient Descent and Perturbed Ascent Algorithm for Nonconvex Functional Constrained Optimization
by: Lu, Songtao
Published: (2022)

Parametrizing Convex Sets Using Sublinear Neural Networks
by: Martinet, Eloi
Published: (2026)

A Natural Primal-Dual Hybrid Gradient Method for Adversarial Neural Network Training on Solving Partial Differential Equations
by: Liu, Shu, et al.
Published: (2024)

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

PRISM: Distribution-free Adaptive Computation of Matrix Functions for Accelerating Neural Network Training
by: Yang, Shenghao, et al.
Published: (2026)

Data driven approach towards more efficient Newton-Raphson power flow calculation for distribution grids
by: Yan, Shengyuan, et al.
Published: (2025)

Accelerated Gradient-based Design Optimization Via Differentiable Physics-Informed Neural Operator: A Composites Autoclave Processing Case Study
by: Patel, Janak M., et al.
Published: (2025)

Control, Optimal Transport and Neural Differential Equations in Supervised Learning
by: Phung, Minh-Nhat, et al.
Published: (2025)

Neural network-enhanced integrators for simulating ordinary differential equations
by: Othmane, Amine, et al.
Published: (2025)

PINNSim: A Simulator for Power System Dynamics based on Physics-Informed Neural Networks
by: Stiasny, Jochen, et al.
Published: (2023)

Neural Operators with Localized Integral and Differential Kernels
by: Liu-Schiaffini, Miguel, et al.
Published: (2024)

CP-PINNs: Data-Driven Changepoints Detection in PDEs Using Online Optimized Physics-Informed Neural Networks
by: Dong, Zhikang, et al.
Published: (2022)

On the Width Scaling of Neural Optimizers Under Matrix Operator Norms I: Row/Column Normalization and Hyperparameter Transfer
by: Xu, Ruihan, et al.
Published: (2026)

Score-Based Physics-Informed Neural Networks for High-Dimensional Fokker-Planck Equations
by: Hu, Zheyuan, et al.
Published: (2024)

FMint: Bridging Human Designed and Data Pretrained Models for Differential Equation Foundation Model
by: Song, Zezheng, et al.
Published: (2024)

Geometric Data Valuation via Leverage Scores
by: Mendoza-Smith, Rodrigo
Published: (2025)

Min-Max Optimisation for Nonconvex-Nonconcave Functions Using a Random Zeroth-Order Extragradient Algorithm
by: Farzin, Amir Ali, et al.
Published: (2025)

Minimisation of Quasar-Convex Functions Using Random Zeroth-Order Oracles
by: Farzin, Amir Ali, et al.
Published: (2025)

Maximum Principle of Optimal Probability Density Control
by: Gaby, Nathan, et al.
Published: (2025)

Transformers Can Implement Preconditioned Richardson Iteration for In-Context Gaussian Kernel Regression
by: Yan, Mingsong, et al.
Published: (2026)

Muon is Not That Special: Random or Inverted Spectra Work Just as Well
by: Shumaylov, Zakhar, et al.
Published: (2026)

Scaling physics-informed hard constraints with mixture-of-experts
by: Chalapathi, Nithin, et al.
Published: (2024)

Learning Explicitly Conditioned Sparsifying Transforms
by: Pătraşcu, Andrei, et al.
Published: (2024)

Examining Policy Entropy of Reinforcement Learning Agents for Personalization Tasks
by: Dereventsov, Anton, et al.
Published: (2022)

A second-order method landing on the Stiefel manifold via Newton$\unicode{x2013}$Schulz iteration
by: Xiong, Xinhui, et al.
Published: (2026)

Physics-informed Neural Networks for Functional Differential Equations: Cylindrical Approximation and Its Convergence Guarantees
by: Miyagawa, Taiki, et al.
Published: (2024)

Physics-Informed Neural Networks for High-Frequency and Multi-Scale Problems using Transfer Learning
by: Mustajab, Abdul Hannan, et al.
Published: (2024)

Neural Port-Hamiltonian Differential Algebraic Equations for Compositional Learning of Electrical Networks
by: Neary, Cyrus, et al.
Published: (2024)

ANaGRAM: A Natural Gradient Relative to Adapted Model for efficient PINNs learning
by: Schwencke, Nilo, et al.
Published: (2024)

Application of Kalman Filter in Stochastic Differential Equations
by: Bao, Wencheng, et al.
Published: (2024)

Universal Approximation of Nonlinear Operators and Their Derivatives
by: de Feo, Filippo
Published: (2026)

Modeling AdaGrad, RMSProp, and Adam with Integro-Differential Equations
by: Heredia, Carlos
Published: (2024)

Physics-Informed Machine Learning for Characterizing System Stability
by: Koike, Tomoki, et al.
Published: (2025)

A comparison between joint and dual UKF implementations for state estimation and leak localization in water distribution networks
by: Romero-Ben, Luis, et al.
Published: (2025)

Data-driven identification of port-Hamiltonian DAE systems by Gaussian processes
by: Zaspel, Peter, et al.
Published: (2024)