Trainable Spline Representations for Physics-Informed Learning

• URL: http://arxiv.org/abs/2607.15751v1
• Date: Fri, 17 Jul 2026 08:39:31 GMT
• Title: Trainable Spline Representations for Physics-Informed Learning
• Abstract summary: Physics-Informed Splines (PI-Splines) is a structured spline-based architecture for physics-informed learning.<n>PI-Splines provide a competitive and stable alternative to neural physics-informed architectures.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: This work introduces Physics-Informed Splines (PI-Splines), a structured spline-based architecture for physics-informed learning. Instead of representing the solution of a differential equation with a neural network, PI-Splines directly parametrize the unknown field through a tensor-product B-spline expansion with trainable control coefficients. This formulation preserves the residual-based training paradigm of Physics-Informed Neural Networks while providing compact support, explicit smoothness control, analytical derivatives, and a direct geometric interpretation of the trainable parameters. When compatible with the spline representation, boundary conditions can be imposed strongly by fixing suitable boundary control coefficients. The proposed method is evaluated on several benchmark problems of increasing difficulty and compared with standard physics-informed frameworks under matched governing equations, collocation sets, loss terms, and optimization procedures, so as to isolate the effect of the approximation architecture. Numerical experiments show that PI-Splines provide a competitive and stable alternative to neural physics-informed architectures, particularly in settings where structured representations, locality, and parameter efficiency are desirable.

Related papers

• Physics-Informed Stochastic Configuration Machine: A Backpropagation-Free Neural Network with Fast Training for Nonlinear Differential Equations [7.927063711454594]
  Physics-In Networks (SCNs) have emerged as a transformative paradigm for solving complex differential equations.<n>Our work provides a highly efficient and scalable foundation for next-generation, real-time Scientific Machine applications.
  arXiv  Detail & Related papers  (2026-08-27T02:40:11Z)
• Physics-Informed Broad Learning System: An Efficient Backpropagation-Free Framework for Solving Partial Differential Equations [9.497148303350697]
  Physics-informed neural networks (PINNs) have emerged as a powerful paradigm for solving partial differential equations (PDEs) by embedding governing physical laws into deep neural networks.<n>We propose a novel physics-informed broad learning system (PI-BLS), the first physics-informed learning framework based on broad RdNNs.<n>PI-BLS offers an efficient learning paradigm for a physics-informed learning framework for solving PDEs that eliminates iterative backpropagation while preserving the underlying physical constraints.
  arXiv  Detail & Related papers  (2026-07-28T11:36:34Z)
• Extending Fourier Neural Operators for Modeling Parameterized and Coupled PDEs [7.368981679765574]
  We extend neural operators with minimal architectural modifications along two directions.<n>For parameterized dynamics, we propose a hypernetwork-based modulation that conditions the operator on physical parameters.<n>For coupled systems, we conduct a systematic exploration of architectural choices.
  arXiv  Detail & Related papers  (2026-07-26T05:28:07Z)
• Adjoint Method versus Physics-Informed Neural Networks in PDE-Constrained Inverse Problems [48.470700002941136]
  Inverse problems governed by partial differential equations (PDEs) are central to computational mechanics and are commonly solved by adjoint-based optimization.<n> physics-informed neural networks (PINNs) have emerged as a flexible alternative.<n>We present a fair comparison of adjoint optimization and PINNs for PDE-constrained inverse problems.
  arXiv  Detail & Related papers  (2026-06-10T17:07:09Z)
• Dynamics and Representation Structure of Local Approximations to Gradient-Based Learning in Linear Recurrent Neural Networks [56.42974363744522]
  We study the learning dynamics of random feedback local online (RFLO) and truncated backpropagation through time (tBPTT)<n>Our work provides analytical insight into how locality constraints shape learning dynamics, with implications for neuroscientific models of learning and alternative optimization approaches for RNNs.
  arXiv  Detail & Related papers  (2026-05-29T18:19:45Z)
• Comparative Study of Bending Analysis using Physics-Informed Neural Networks and Numerical Dynamic Deflection in Perforated nanobeam [0.0]
  Theory of functional connections (TFC) systematically embed governing differential equation constraints into a constrained expression (CE)<n>Within this framework, the free function appearing in the constrained expression is expressed through a functional link neural network (FLNN)<n>Relationship between static and dynamic defection of simply-supported (Sbeam-S) perforated nanobeams has been investigated here.
  arXiv  Detail & Related papers  (2026-04-15T06:13:00Z)
• Physics-informed neural networks for solving saddle-point equations in strong-field physics with tailored fields [0.8520624117635327]
  We develop an unsupervised physics-informed neural network to solve saddle-point equations.<n>We benchmark the PINN against a conventional solver for a range of fields.<n>We compute coherent ATI photoelectron momentum distributions and show the symmetries of the driving fields are reflected in both the saddle-point structure and the resulting spectra.
  arXiv  Detail & Related papers  (2026-03-16T18:12:44Z)
• Graph-Instructed Neural Networks for parametric problems with varying boundary conditions [0.0]
  This work addresses the accurate and efficient simulation of physical phenomena governed by parametric Partial Differential Equations (PDEs)<n>We propose a novel methodology based on Graph-Instructed Neural Networks (GINNs)
  arXiv  Detail & Related papers  (2026-03-09T12:26:53Z)
• From Coefficients to Directions: Rethinking Model Merging with Directional Alignment [66.99062575537555]
  We introduce a unified geometric framework, emphMerging with Directional Alignment (method), which aligns directional structures consistently in both the parameter and feature spaces.<n>Our analysis shows that directional alignment improves structural coherence, and extensive experiments across benchmarks, model scales, and task configurations further validate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2025-11-29T08:40:58Z)
• Physics-Informed Deep B-Spline Networks [4.593829882136678]
  We propose physics-informed deep B-spline networks for learning partial differential equations.<n>B-spline networks approximate a family of PDEs with different parameters and ICBCs by learning B-spline control points through neural networks.<n>We show that B-spline networks are universal approximators for such families under mild conditions.
  arXiv  Detail & Related papers  (2025-03-21T01:15:40Z)
• Physics-aware deep learning framework for linear elasticity [0.0]
  The paper presents an efficient and robust data-driven deep learning (DL) computational framework for linear continuum elasticity problems. For an accurate representation of the field variables, a multi-objective loss function is proposed. Several benchmark problems including the Airimaty solution to elasticity and the Kirchhoff-Love plate problem are solved.
  arXiv  Detail & Related papers  (2023-02-19T20:33:32Z)
• Tunable Complexity Benchmarks for Evaluating Physics-Informed Neural Networks on Coupled Ordinary Differential Equations [64.78260098263489]
  In this work, we assess the ability of physics-informed neural networks (PINNs) to solve increasingly-complex coupled ordinary differential equations (ODEs) We show that PINNs eventually fail to produce correct solutions to these benchmarks as their complexity increases. We identify several reasons why this may be the case, including insufficient network capacity, poor conditioning of the ODEs, and high local curvature, as measured by the Laplacian of the PINN loss.
  arXiv  Detail & Related papers  (2022-10-14T15:01:32Z)
• Neural Operator with Regularity Structure for Modeling Dynamics Driven by SPDEs [70.51212431290611]
  Partial differential equations (SPDEs) are significant tools for modeling dynamics in many areas including atmospheric sciences and physics. We propose the Neural Operator with Regularity Structure (NORS) which incorporates the feature vectors for modeling dynamics driven by SPDEs. We conduct experiments on various of SPDEs including the dynamic Phi41 model and the 2d Navier-Stokes equation.
  arXiv  Detail & Related papers  (2022-04-13T08:53:41Z)
• Provably Efficient Neural Estimation of Structural Equation Model: An Adversarial Approach [144.21892195917758]
  We study estimation in a class of generalized Structural equation models (SEMs) We formulate the linear operator equation as a min-max game, where both players are parameterized by neural networks (NNs), and learn the parameters of these neural networks using a gradient descent. For the first time we provide a tractable estimation procedure for SEMs based on NNs with provable convergence and without the need for sample splitting.
  arXiv  Detail & Related papers  (2020-07-02T17:55:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.