Cover Image

Accelerating Natural Gradient Descent for PINNs with Randomized Numerical Linear Algebra

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Bioli, Ivan, Marcati, Carlo, Sangalli, Giancarlo
Format:	Preprint
Published:	2025
Subjects:	Numerical Analysis Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Recent and Upcoming Developments in Randomized Numerical Linear Algebra for Machine Learning
by: Dereziński, Michał, et al.
Published: (2024)

Streaming Krylov-Accelerated Stochastic Gradient Descent
by: Thomas, Stephen
Published: (2025)

Preconditioning for Accelerated Gradient Descent Optimization and Regularization
by: Ye, Qiang
Published: (2024)

Sketch 'n Solve: An Efficient Python Package for Large-Scale Least Squares Using Randomized Numerical Linear Algebra
by: Lavaee, Alex
Published: (2024)

Accelerating Fractional PINNs using Operational Matrices of Derivative
by: Taheri, Tayebeh, et al.
Published: (2024)

Learning from Linear Algebra: A Graph Neural Network Approach to Preconditioner Design for Conjugate Gradient Solvers
by: Trifonov, Vladislav, et al.
Published: (2024)

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

Gradient Descent as a Perceptron Algorithm: Understanding Dynamics and Implicit Acceleration
by: Tyurin, Alexander
Published: (2025)

Foundations of Polar Linear Algebra
by: Guasti, Giovanni
Published: (2026)

RL-PINNs: Reinforcement Learning-Driven Adaptive Sampling for Efficient Training of PINNs
by: Song, Zhenao
Published: (2025)

Integral regularization PINNs for evolution equations
by: Feng, Xiaodong, et al.
Published: (2025)

Auto-Adaptive PINNs with Applications to Phase Transitions
by: Buck, Kevin, et al.
Published: (2025)

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

E-PINNs: Epistemic Physics-Informed Neural Networks
by: Jacob, Bruno, et al.
Published: (2025)

Multi-Preconditioned LBFGS for Training Finite-Basis PINNs
by: Salvadó-Benasco, Marc, et al.
Published: (2026)

Super Gradient Descent: Global Optimization requires Global Gradient
by: Achour, Seifeddine
Published: (2024)

One-Shot Transfer Learning for Nonlinear PDEs with Perturbative PINNs
by: Auroy, Samuel, et al.
Published: (2025)

Using Parametric PINNs for Predicting Internal and External Turbulent Flows
by: Ghosh, Shinjan, et al.
Published: (2024)

TGPT-PINN: Nonlinear model reduction with transformed GPT-PINNs
by: Chen, Yanlai, et al.
Published: (2024)

High precision PINNs in unbounded domains: application to singularity formulation in PDEs
by: Wang, Yixuan, et al.
Published: (2025)

Beyond Derivative Pathology of PINNs: Variable Splitting Strategy with Convergence Analysis
by: Park, Yesom, et al.
Published: (2024)

Deflation-PINNs: Learning Multiple Solutions for PDEs and Landau-de Gennes
by: Disarò, Sean, et al.
Published: (2026)

Provably Faster Gradient Descent via Long Steps
by: Grimmer, Benjamin
Published: (2023)

PINNsFailureRegion Localization and Refinement through White-box AdversarialAttack
by: Shi, Shengzhu, et al.
Published: (2023)

Boundary condition enforcement with PINNs: a comparative study and verification on 3D geometries
by: Rowan, Conor, et al.
Published: (2025)

Certified machine learning: Rigorous a posteriori error bounds for PDE defined PINNs
by: Hillebrecht, Birgit, et al.
Published: (2022)

Stochastic Dimension Implicit Functional Projections for Exact Integral Conservation in High-Dimensional PINNs
by: Liang, Zhangyong
Published: (2026)

PINNs error estimates for nonlinear equations in $\mathbb{R}$-smooth Banach spaces
by: Gao, Jiexing, et al.
Published: (2023)

Expression Rates of Neural Operators for Linear Elliptic PDEs in Polytopes
by: Marcati, Carlo, et al.
Published: (2024)

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

SVD-PINNs: Transfer Learning of Physics-Informed Neural Networks via Singular Value Decomposition
by: Gao, Yihang, et al.
Published: (2022)

Sparsity for Infinite-Parametric Holomorphic Functions on Gaussian Spaces
by: Marcati, Carlo, et al.
Published: (2025)

Investigating the Ability of PINNs To Solve Burgers' PDE Near Finite-Time BlowUp
by: Kumar, Dibyakanti, et al.
Published: (2023)

Dual Cone Gradient Descent for Training Physics-Informed Neural Networks
by: Hwang, Youngsik, et al.
Published: (2024)

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

Quantile-Based Randomized Kaczmarz for Corrupted Tensor Linear Systems
by: Castillo, Alejandra, et al.
Published: (2025)

Geometry-aware PINNs for Turbulent Flow Prediction
by: Ghosh, Shinjan, et al.
Published: (2024)

Random Neural Network Expressivity for Non-Linear Partial Differential Equations
by: Mehmood, Muhammed Ali, et al.
Published: (2026)

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

Gradient is All You Need? How Consensus-Based Optimization can be Interpreted as a Stochastic Relaxation of Gradient Descent
by: Riedl, Konstantin, et al.
Published: (2023)