Solved in Unit Domain: JacobiNet for Differentiable Coordinate-Transformed PINNs

• URL: http://arxiv.org/abs/2508.02537v2
• Date: Mon, 15 Sep 2025 03:42:13 GMT
• Title: Solved in Unit Domain: JacobiNet for Differentiable Coordinate-Transformed PINNs
• Abstract summary: JacobiNet is a learning-based coordinate-transformed PINN framework.<n>It mitigates domain mapping and PDE solving within an end-to-end differentiable architecture.<n>It improves prediction accuracy by an average of 3.65*, while delivering over 10* speed up-demonstrating strong generalization, accuracy, and efficiency.
• Score: 8.879523745749973
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Physics-Informed Neural Networks offer a powerful framework for solving PDEs by embedding physical laws into the learning process. However, when applied to domains with irregular boundaries, PINNs often suffer from instability and slow convergence, which stems from (1) inconsistent normalization due to geometric anisotropy, (2) inaccurate boundary enforcements, and (3) imbalanced loss term competition. A common workaround is to map the domain to a regular space. Yet, conventional mapping methods rely on case-specific meshes, define Jacobians at pre-specified fixed nodes, reformulate PDEs via the chain rule-making them incompatible with modern automatic differentiation, tensor-based frameworks. To bridge this gap, we propose JacobiNet, a learning-based coordinate-transformed PINN framework that unifies domain mapping and PDE solving within an end-to-end differentiable architecture. Leveraging lightweight MLPs, JacobiNet learns continuous, differentiable mappings, enables direct Jacobian computation via autograd, shares computation graph with downstream PINNs. Its continuous nature and built-in Jacobian eliminate the need for meshing, explicit Jacobians computation/ storage, and PDE reformulation, while unlocking geometric-editing operations, reducing the mapping cost. Separating physical modeling from geometric complexity, JacobiNet (1) addresses normalization challenges in the original anisotropic coordinates, (2) facilitates hard constraints of boundary conditions, and (3) mitigates the long-standing imbalance among loss terms. Evaluated on various PDEs, JacobiNet reduces the L2 error from 0.11-0.73 to 0.01-0.09. In vessel-like domains with varying shapes, JacobiNet enables millisecond-level mapping inference for unseen geometries, improves prediction accuracy by an average of 3.65*, while delivering over 10* speed up-demonstrating strong generalization, accuracy, and efficiency.

Related papers

• Tackling Failure Modes of PINNs and PIKANs Using Conflict-Free Gradients [0.30586855806896046]
  We bridge domain decomposition with projection-based gradient surgery to mitigate conflicting gradients that degrade training.<n>We show that Norm-PCGrad consistently achieves the lowest relative $L$ error compared to training without gradient surgery.<n>We additionally demonstrate that gradient surgery extends to physics-informed Kolmogorov-Arnold Networks (KANPIs) yielding substantial accuracy improvements for 3D domain decomposition.
  arXiv  Detail & Related papers  (2026-09-13T23:22:05Z)
• 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)
• Neural-Schwarz Tiling for Geometry-Universal PDE Solving at Scale [0.0]
  We introduce $textbfNEST$ ($textbfS$chwarz $textbfT$iling), a local-to-global framework that shifts learning from full-domain solution operators to reusable local physical solvers.<n>NEST learns a neural operator on minimal voxel patches with diverse local geometries and boundary/interface data.<n>Our results show that local neural building blocks, coupled through Schwarz iteration, offer a reusable local-training path toward scalable learned PDE solvers.
  arXiv  Detail & Related papers  (2026-05-12T16:20:26Z)
• 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)
• Rethinking Input Domains in Physics-Informed Neural Networks via Geometric Compactification Mappings [17.201530991184814]
  We introduce a mapping paradigm that reshapes the input coordinates through differentiable geometric compactification mappings.<n>We show that this approach yields more uniform residual distributions and higher solution accuracy on representative 1D and 2D PDEs.
  arXiv  Detail & Related papers  (2026-02-18T05:27:53Z)
• Boundary condition enforcement with PINNs: a comparative study and verification on 3D geometries [0.0]
  Physics-informed neural networks (PINNs) have been studied extensively as a novel technique for solving forward and inverse problems in physics and engineering.<n>There have been limited studies of PINNs on complex three-dimensional geometries, as the lack of mesh and the reliance on the strong form of the partial differential equation (PDE) make boundary condition enforcement challenging.<n>This work represents a step in the direction of establishing PINNs as a mature numerical method, capable of competing head-to-head with incumbents such as the finite element method.
  arXiv  Detail & Related papers  (2025-12-16T22:15:01Z)
• Adaptive Mesh-Quantization for Neural PDE Solvers [51.26961483962011]
  Graph Neural Networks can handle the irregular meshes required for complex geometries and boundary conditions, but still apply uniform computational effort across all nodes.<n>We propose Adaptive Mesh Quantization: spatially adaptive quantization across mesh node, edge, and cluster features, dynamically adjusting the bit-width used by a quantized model.<n>We demonstrate our framework's effectiveness by integrating it with two state-of-the-art models, MP-PDE and GraphViT, to evaluate performance across multiple tasks.
  arXiv  Detail & Related papers  (2025-11-23T14:47:24Z)
• UGM2N: An Unsupervised and Generalizable Mesh Movement Network via M-Uniform Loss [17.62415278198884]
  Mesh movement techniques enhance both simulation accuracy and computational efficiency.<n>Existing approaches suffer from high computational complexity and geometric inflexibility.<n>We present an Unsupervised and Generalizable Mesh Movement Network (UGM2N)
  arXiv  Detail & Related papers  (2025-08-12T03:56:45Z)
• Data-Driven Adaptive Gradient Recovery for Unstructured Finite Volume Computations [0.0]
  We present a novel data-driven approach for enhancing gradient reconstruction in unstructured finite volume methods for hyperbolic conservation laws.<n>Our approach extends previous structured-grid methodologies to unstructured meshes through a modified DeepONet architecture.<n>The proposed algorithm is faster and more accurate than the traditional second-order finite volume solver.
  arXiv  Detail & Related papers  (2025-07-22T13:23:57Z)
• Physics-Informed Neural Networks with Hard Nonlinear Equality and Inequality Constraints [0.0]
  KKT-Hardnet is a PINN architecture that enforces both linear and nonlinear equality and inequality constraints up to machine precision.<n>We apply KKT-Hardnet on both test problems and a real-world chemical process simulation.
  arXiv  Detail & Related papers  (2025-07-10T19:24:53Z)
• PhysicsCorrect: A Training-Free Approach for Stable Neural PDE Simulations [4.7903561901859355]
  We present PhysicsCorrect, a training-free correction framework that enforces PDE consistency at each prediction step.<n>Our key innovation is an efficient caching strategy that precomputes the Jacobian and its pseudoinverse during an offline warm-up phase.<n>Across three representative PDE systems, PhysicsCorrect reduces prediction errors by up to 100x while adding negligible inference time.
  arXiv  Detail & Related papers  (2025-07-03T01:22:57Z)
• Learning based convex approximation for constrained parametric optimization [11.379408842026981]
  We propose an input neural network (ICNN)-based self-supervised learning framework to solve constrained optimization problems.<n>We provide rigorous convergence analysis, showing that the framework converges to a Karush-Kuhn-Tucker (KKT) approximation point of the original problem.<n>Our approach achieves a superior balance among accuracy, feasibility, and computational efficiency.
  arXiv  Detail & Related papers  (2025-05-07T00:33:14Z)
• Enabling Automatic Differentiation with Mollified Graph Neural Operators [75.3183193262225]
  We propose the mollified graph neural operator (mGNO), the first method to leverage automatic differentiation and compute emphexact gradients on arbitrary geometries.<n>For a PDE example on regular grids, mGNO paired with autograd reduced the L2 relative data error by 20x compared to finite differences.<n>It can also solve PDEs on unstructured point clouds seamlessly, using physics losses only, at resolutions vastly lower than those needed for finite differences to be accurate enough.
  arXiv  Detail & Related papers  (2025-04-11T06:16:30Z)
• General-Kindred Physics-Informed Neural Network to the Solutions of Singularly Perturbed Differential Equations [11.121415128908566]
  We propose the General-Kindred Physics-Informed Neural Network (GKPINN) for solving Singular Perturbation Differential Equations (SPDEs) This approach utilizes prior knowledge of the boundary layer from the equation and establishes a novel network to assist PINN in approxing the boundary layer. The research findings underscore the exceptional performance of our novel approach, GKPINN, which delivers a remarkable enhancement in reducing the $L$ error by two to four orders of magnitude compared to the established PINN methodology.
  arXiv  Detail & Related papers  (2024-08-27T02:03:22Z)
• RoPINN: Region Optimized Physics-Informed Neural Networks [66.38369833561039]
  Physics-informed neural networks (PINNs) have been widely applied to solve partial differential equations (PDEs) This paper proposes and theoretically studies a new training paradigm as region optimization. A practical training algorithm, Region Optimized PINN (RoPINN), is seamlessly derived from this new paradigm.
  arXiv  Detail & Related papers  (2024-05-23T09:45:57Z)
• Stable Nonconvex-Nonconcave Training via Linear Interpolation [51.668052890249726]
  This paper presents a theoretical analysis of linearahead as a principled method for stabilizing (large-scale) neural network training. We argue that instabilities in the optimization process are often caused by the nonmonotonicity of the loss landscape and show how linear can help by leveraging the theory of nonexpansive operators.
  arXiv  Detail & Related papers  (2023-10-20T12:45:12Z)
• A multiobjective continuation method to compute the regularization path of deep neural networks [1.3654846342364308]
  Sparsity is a highly feature in deep neural networks (DNNs) since it ensures numerical efficiency, improves the interpretability of models, and robustness. We present an algorithm that allows for the entire sparse front for the above-mentioned objectives in a very efficient manner for high-dimensional gradients with millions of parameters. We demonstrate that knowledge of the regularization path allows for a well-generalizing network parametrization.
  arXiv  Detail & Related papers  (2023-08-23T10:08:52Z)
• Constrained Optimization via Exact Augmented Lagrangian and Randomized Iterative Sketching [55.28394191394675]
  We develop an adaptive inexact Newton method for equality-constrained nonlinear, nonIBS optimization problems. We demonstrate the superior performance of our method on benchmark nonlinear problems, constrained logistic regression with data from LVM, and a PDE-constrained problem.
  arXiv  Detail & Related papers  (2023-05-28T06:33:37Z)
• Adaptive Self-supervision Algorithms for Physics-informed Neural Networks [59.822151945132525]
  Physics-informed neural networks (PINNs) incorporate physical knowledge from the problem domain as a soft constraint on the loss function. We study the impact of the location of the collocation points on the trainability of these models. We propose a novel adaptive collocation scheme which progressively allocates more collocation points to areas where the model is making higher errors.
  arXiv  Detail & Related papers  (2022-07-08T18:17:06Z)
• Adaptivity and Non-stationarity: Problem-dependent Dynamic Regret for Online Convex Optimization [70.4342220499858]
  We introduce novel online algorithms that can exploit smoothness and replace the dependence on $T$ in dynamic regret with problem-dependent quantities. Our results are adaptive to the intrinsic difficulty of the problem, since the bounds are tighter than existing results for easy problems and safeguard the same rate in the worst case.
  arXiv  Detail & Related papers  (2021-12-29T02:42:59Z)
• Local AdaGrad-Type Algorithm for Stochastic Convex-Concave Minimax Problems [80.46370778277186]
  Large scale convex-concave minimax problems arise in numerous applications, including game theory, robust training, and training of generative adversarial networks. We develop a communication-efficient distributed extragrad algorithm, LocalAdaSient, with an adaptive learning rate suitable for solving convex-concave minimax problem in the. Server model. We demonstrate its efficacy through several experiments in both the homogeneous and heterogeneous settings.
  arXiv  Detail & Related papers  (2021-06-18T09:42:05Z)
• dNNsolve: an efficient NN-based PDE solver [62.997667081978825]
  We introduce dNNsolve, that makes use of dual Neural Networks to solve ODEs/PDEs. We show that dNNsolve is capable of solving a broad range of ODEs/PDEs in 1, 2 and 3 spacetime dimensions.
  arXiv  Detail & Related papers  (2021-03-15T19:14:41Z)
• ResNet-LDDMM: Advancing the LDDMM Framework Using Deep Residual Networks [86.37110868126548]
  In this work, we make use of deep residual neural networks to solve the non-stationary ODE (flow equation) based on a Euler's discretization scheme. We illustrate these ideas on diverse registration problems of 3D shapes under complex topology-preserving transformations.
  arXiv  Detail & Related papers  (2021-02-16T04:07:13Z)
• PFNN: A Penalty-Free Neural Network Method for Solving a Class of Second-Order Boundary-Value Problems on Complex Geometries [4.620110353542715]
  We present PFNN, a penalty-free neural network method, to solve a class of second-order boundary-value problems. PFNN is superior to several existing approaches in terms of accuracy, flexibility and robustness.
  arXiv  Detail & Related papers  (2020-04-14T13:36:14Z)

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.