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

• URL: http://arxiv.org/abs/2511.15530v1
• Date: Wed, 19 Nov 2025 15:29:42 GMT
• Title: Convergence and Sketching-Based Efficient Computation of Neural Tangent Kernel Weights in Physics-Based Loss
• Authors: Max Hirsch, Federico Pichi,
• Abstract summary: We show that gradient descent enhanced with adaptive NTK-based weights is convergent in a suitable sense.<n>We then address the problem of computational efficiency by developing a randomized algorithm inspired by a predictor-corrector approach and matrix sketching.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In multi-objective optimization, multiple loss terms are weighted and added together to form a single objective. These weights are chosen to properly balance the competing losses according to some meta-goal. For example, in physics-informed neural networks (PINNs), these weights are often adaptively chosen to improve the network's generalization error. A popular choice of adaptive weights is based on the neural tangent kernel (NTK) of the PINN, which describes the evolution of the network in predictor space during training. The convergence of such an adaptive weighting algorithm is not clear a priori. Moreover, these NTK-based weights would be updated frequently during training, further increasing the computational burden of the learning process. In this paper, we prove that under appropriate conditions, gradient descent enhanced with adaptive NTK-based weights is convergent in a suitable sense. We then address the problem of computational efficiency by developing a randomized algorithm inspired by a predictor-corrector approach and matrix sketching, which produces unbiased estimates of the NTK up to an arbitrarily small discretization error. Finally, we provide numerical experiments to support our theoretical findings and to show the efficacy of our randomized algorithm. Code Availability: https://github.com/maxhirsch/Efficient-NTK

Related papers

• Faster Predictive Coding Networks via Better Initialization [52.419343840654186]
  We propose a new technique for predictive coding networks that aims to preserve the iterative progress made on previous training samples.<n>Our experiments demonstrate substantial improvements in convergence speed and final test loss in both supervised and unsupervised settings.
  arXiv  Detail & Related papers  (2026-01-28T08:52:19Z)
• Convolution-weighting method for the physics-informed neural network: A Primal-Dual Optimization Perspective [14.65008276932511]
  Physics-informed neural networks (PINNs) are extensively employed to solve partial differential equations (PDEs)<n>PINNs are typically optimized using a finite set of points, which poses significant challenges in guaranteeing their convergence and accuracy.<n>We propose a new weighting scheme that will adaptively change the weights to the loss functions from isolated points to their continuous neighborhood regions.
  arXiv  Detail & Related papers  (2025-06-24T17:13:51Z)
• Concurrent Training and Layer Pruning of Deep Neural Networks [0.0]
  We propose an algorithm capable of identifying and eliminating irrelevant layers of a neural network during the early stages of training. We employ a structure using residual connections around nonlinear network sections that allow the flow of information through the network once a nonlinear section is pruned.
  arXiv  Detail & Related papers  (2024-06-06T23:19:57Z)
• Enriched Physics-informed Neural Networks for Dynamic Poisson-Nernst-Planck Systems [0.8192907805418583]
  This paper proposes a meshless deep learning algorithm, enriched physics-informed neural networks (EPINNs) to solve dynamic Poisson-Nernst-Planck (PNP) equations. The EPINNs takes the traditional physics-informed neural networks as the foundation framework, and adds the adaptive loss weight to balance the loss functions. Numerical results indicate that the new method has better applicability than traditional numerical methods in solving such coupled nonlinear systems.
  arXiv  Detail & Related papers  (2024-02-01T02:57:07Z)
• Equivariant Deep Weight Space Alignment [54.65847470115314]
  We propose a novel framework aimed at learning to solve the weight alignment problem. We first prove that weight alignment adheres to two fundamental symmetries and then, propose a deep architecture that respects these symmetries.
  arXiv  Detail & Related papers  (2023-10-20T10:12:06Z)
• 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)
• Where Should We Begin? A Low-Level Exploration of Weight Initialization Impact on Quantized Behaviour of Deep Neural Networks [93.4221402881609]
  We present an in-depth, fine-grained ablation study of the effect of different weights initialization on the final distributions of weights and activations of different CNN architectures. To our best knowledge, we are the first to perform such a low-level, in-depth quantitative analysis of weights initialization and its effect on quantized behaviour.
  arXiv  Detail & Related papers  (2020-11-30T06:54:28Z)
• Self-Adaptive Physics-Informed Neural Networks using a Soft Attention Mechanism [1.6114012813668932]
  Physics-Informed Neural Networks (PINNs) have emerged as a promising application of deep neural networks to the numerical solution of nonlinear partial differential equations (PDEs) We propose a fundamentally new way to train PINNs adaptively, where the adaptation weights are fully trainable and applied to each training point individually. In numerical experiments with several linear and nonlinear benchmark problems, the SA-PINN outperformed other state-of-the-art PINN algorithm in L2 error.
  arXiv  Detail & Related papers  (2020-09-07T04:07:52Z)
• Neural networks with late-phase weights [66.72777753269658]
  We show that the solutions found by SGD can be further improved by ensembling a subset of the weights in late stages of learning. At the end of learning, we obtain back a single model by taking a spatial average in weight space.
  arXiv  Detail & Related papers  (2020-07-25T13:23:37Z)
• Revisiting Initialization of Neural Networks [72.24615341588846]
  We propose a rigorous estimation of the global curvature of weights across layers by approximating and controlling the norm of their Hessian matrix. Our experiments on Word2Vec and the MNIST/CIFAR image classification tasks confirm that tracking the Hessian norm is a useful diagnostic tool.
  arXiv  Detail & Related papers  (2020-04-20T18:12:56Z)
• Distance-Based Regularisation of Deep Networks for Fine-Tuning [116.71288796019809]
  We develop an algorithm that constrains a hypothesis class to a small sphere centred on the initial pre-trained weights. Empirical evaluation shows that our algorithm works well, corroborating our theoretical results.
  arXiv  Detail & Related papers  (2020-02-19T16:00:47Z)

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.