Imagen de Portada

Convergence and Sketching-Based Efficient Computation of Neural Tangent Kernel Weights in Physics-Based Loss

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Hirsch, Max, Pichi, Federico
Formato:	Preprint
Publicado:	2025
Materias:	Numerical Analysis Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Neural empirical interpolation method for nonlinear model reduction
por: Hirsch, Max, et al.
Publicado: (2024)

Latent Dynamics Graph Convolutional Networks for model order reduction of parameterized time-dependent PDEs
por: Tomada, Lorenzo, et al.
Publicado: (2026)

GFN: A graph feedforward network for resolution-invariant reduced operator learning in multifidelity applications
por: Morrison, Oisín M., et al.
Publicado: (2024)

Integrating Artificial Intelligence, Physics, and Internet of Things: A Framework for Cultural Heritage Conservation
por: Valentino, Carmine, et al.
Publicado: (2026)

Time Extrapolation with Graph Convolutional Autoencoder and Tensor Train Decomposition
por: Chen, Yuanhong, et al.
Publicado: (2025)

Nonlocal Neural Tangent Kernels via Parameter-Space Interactions
por: Nagaraj, Sriram, et al.
Publicado: (2025)

Sketching the Heat Kernel: Using Gaussian Processes to Embed Data
por: Gilbert, Anna C., et al.
Publicado: (2024)

Quantifying Training Difficulty and Accelerating Convergence in Neural Network-Based PDE Solvers
por: Chen, Chuqi, et al.
Publicado: (2024)

On the Convergence of Irregular Sampling in Reproducing Kernel Hilbert Spaces
por: Iske, Armin
Publicado: (2025)

Fast Neural Tangent Kernel Alignment, Norm and Effective Rank via Trace Estimation
por: Hazelden, James
Publicado: (2025)

Optimal Transport-inspired Deep Learning Framework for Slow-Decaying Kolmogorov n-width Problems: Exploiting Sinkhorn Loss and Wasserstein Kernel
por: Khamlich, Moaad, et al.
Publicado: (2023)

Convergence of Stochastic Gradient Methods for Wide Two-Layer Physics-Informed Neural Networks
por: Jin, Bangti, et al.
Publicado: (2025)

Pruning AMR: Efficient Visualization of Implicit Neural Representations via Weight Matrix Analysis
por: Zvonek, Jennifer, et al.
Publicado: (2025)

An Orthogonal Polynomial Kernel-Based Machine Learning Model for Differential-Algebraic Equations
por: Taheri, Tayebeh, et al.
Publicado: (2024)

Convex-Geometric Error Bounds for Positive-Weight Kernel Quadrature
por: Hayakawa, Satoshi
Publicado: (2026)

Sketching Low-Rank Plus Diagonal Matrices
por: Fernandez, Andres, et al.
Publicado: (2025)

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

Computational Advantages of Multi-Grade Deep Learning: Convergence Analysis and Performance Insights
por: Fang, Ronglong, et al.
Publicado: (2025)

Learning from Integral Losses in Physics Informed Neural Networks
por: Saleh, Ehsan, et al.
Publicado: (2023)

Solving Roughly Forced Nonlinear PDEs via Misspecified Kernel Methods and Neural Networks
por: Baptista, Ricardo, et al.
Publicado: (2025)

Kernel Neural Operators (KNOs) for Scalable, Memory-efficient, Geometrically-flexible Operator Learning
por: Lowery, Matthew, et al.
Publicado: (2024)

Learning Neural PDE Solvers with Convergence Guarantees
por: Hsieh, Jun-Ting, et al.
Publicado: (2019)

Efficient Numerical Integration in Reproducing Kernel Hilbert Spaces via Leverage Scores Sampling
por: Chatalic, Antoine, et al.
Publicado: (2023)

Neural Parameter Regression for Explicit Representations of PDE Solution Operators
por: Mundinger, Konrad, et al.
Publicado: (2024)

Scalable Signature Kernel Computations for Long Time Series via Local Neumann Series Expansions
por: Tamayo-Rios, Matthew, et al.
Publicado: (2025)

Data-Efficient Kernel Methods for Learning Differential Equations and Their Solution Operators: Algorithms and Error Analysis
por: Jalalian, Yasamin, et al.
Publicado: (2025)

Fast Evaluation of Additive Kernels: Feature Arrangement, Fourier Methods, and Kernel Derivatives
por: Wagner, Theresa, et al.
Publicado: (2024)

Beyond Regular Grids: Fourier-Based Neural Operators on Arbitrary Domains
por: Lingsch, Levi, et al.
Publicado: (2023)

Constrained or Unconstrained? Neural-Network-Based Equation Discovery from Data
por: Norman, Grant, et al.
Publicado: (2024)

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

Multivariate Density Estimation via Variance-Reduced Sketching
por: Peng, Yifan, et al.
Publicado: (2024)

A Computationally Efficient Multidimensional Vision Transformer
por: Ichi, Alaa El, et al.
Publicado: (2026)

Gradient Flow Based Phase-Field Modeling Using Separable Neural Networks
por: Mattey, Revanth, et al.
Publicado: (2024)

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

A Convergent Finite Element Scheme for the Q-Tensor Model of Liquid Crystals Subjected to an Electric Field
por: Hirsch, Max, et al.
Publicado: (2023)

Predicting Wave Dynamics using Deep Learning with Multistep Integration Inspired Attention and Physics-Based Loss Decomposition
por: Deo, Indu Kant, et al.
Publicado: (2025)

Data-Efficient Neural Operator Training via Physics-Based Active Learning
por: Polanska, Alicja, et al.
Publicado: (2026)

KROM: Kernelized Reduced Order Modeling
por: Bacho, Aras, et al.
Publicado: (2026)

In Situ Training of Implicit Neural Compressors for Scientific Simulations via Sketch-Based Regularization
por: Simpson, Cooper, et al.
Publicado: (2025)

Radial Müntz-Szász Networks: Neural Architectures with Learnable Power Bases for Multidimensional Singularities
por: N'guessan, Gnankan Landry Regis, et al.
Publicado: (2026)