Dual Natural Gradient Descent for Scalable Training of Physics-Informed Neural Networks

• URL: http://arxiv.org/abs/2505.21404v2
• Date: Wed, 08 Oct 2025 17:39:20 GMT
• Title: Dual Natural Gradient Descent for Scalable Training of Physics-Informed Neural Networks
• Abstract summary: Natural-gradient methods markedly accelerate the training of Physics-Informed Neural Networks (PINNs)<n>We introduce textitDual Natural Gradient Descent (D-NGD)<n>D-NGD computes the Gauss--Newton step in residual space, augments it with a geodesic-acceleration correction at negligible extra cost, and provides both a dense direct solver for modest $m$ and a Nystrom-preconditioned conjugate-gradient solver for larger $m$.
• Score: 0.7562843347215286
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Natural-gradient methods markedly accelerate the training of Physics-Informed Neural Networks (PINNs), yet their Gauss--Newton update must be solved in the parameter space, incurring a prohibitive $O(n^3)$ time complexity, where $n$ is the number of network trainable weights. We show that exactly the same step can instead be formulated in a generally smaller residual space of size $m = \sum_{\gamma} N_{\gamma} d_{\gamma}$, where each residual class $\gamma$ (e.g. PDE interior, boundary, initial data) contributes $N_{\gamma}$ collocation points of output dimension $d_{\gamma}$. Building on this insight, we introduce \textit{Dual Natural Gradient Descent} (D-NGD). D-NGD computes the Gauss--Newton step in residual space, augments it with a geodesic-acceleration correction at negligible extra cost, and provides both a dense direct solver for modest $m$ and a Nystrom-preconditioned conjugate-gradient solver for larger $m$. Experimentally, D-NGD scales second-order PINN optimization to networks with up to 12.8 million parameters, delivers one- to three-order-of-magnitude lower final error $L^2$ than first-order methods (Adam, SGD) and quasi-Newton methods, and -- crucially -- enables natural-gradient training of PINNs at this scale on a single GPU.

Related papers

• An Optimisation Framework for the Well-Conditioned Training of Physics-Informed Neural Networks [0.12744523252873352]
  Physics-informed neural networks (PINNs) have emerged as a promising route to solve partial differential equations.<n>PINNs have struggled to reach the precision of classical solvers.<n>We present $textbfDSGNAR$: Doubly-Sketched Gauss-Newton with Adaptive Ratio, a scalable second-order optimisation framework.
  arXiv  Detail & Related papers  (2026-07-02T14:03:34Z)
• How Neural Reward Models Learn Features for Policy Optimization: A Single-Index Analysis [53.063298916923976]
  We study the feedback in a Gaussian single-index model with $r*(x) = *(langle *, xrangle)$ and $x sim N(0, I_d)$.<n>We analyze a two-stage neural reward model that first learns the hidden direction $*$ from reward-weighted samples and then fits the readout layer by weighted ridge regression.
  arXiv  Detail & Related papers  (2026-05-23T22:00:38Z)
• FFT-Accelerated Auxiliary Variable MCMC for Fermionic Lattice Models: A Determinant-Free Approach with $O(N\log N)$ Complexity [52.3171766248012]
  We introduce a Markov Chain Monte Carlo (MCMC) algorithm that dramatically accelerates the simulation of quantum many-body systems.<n>We validate our algorithm on benchmark quantum physics problems, accurately reproducing known theoretical results.<n>Our work provides a powerful tool for large-scale probabilistic inference and opens avenues for physics-inspired generative models.
  arXiv  Detail & Related papers  (2025-10-13T07:57:21Z)
• Emergence and scaling laws in SGD learning of shallow neural networks [64.48316762675141]
  We study the complexity of online gradient descent (SGD) for learning a two-layer neural network with $P$ neurons on isotropic Gaussian data.<n>We provide a precise analysis of SGD dynamics for the training of a student two-layer network to minimize the mean squared error (MSE) objective.
  arXiv  Detail & Related papers  (2025-04-28T16:58:55Z)
• 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)
• Sharp Generalization for Nonparametric Regression in Interpolation Space by Over-Parameterized Neural Networks Trained with Preconditioned Gradient Descent and Early Stopping [15.975065054204753]
  We study non regression using an over-parametricized two-layer neural networks trained with algorithmic guarantees.<n>We demonstrate that training the neural network with a novel Preconditioned Gradient Descent (PGD) algorithm, equipped with early stopping, achieves a sharp regression rate.
  arXiv  Detail & Related papers  (2024-07-16T03:38:34Z)
• Bayesian Inference with Deep Weakly Nonlinear Networks [57.95116787699412]
  We show at a physics level of rigor that Bayesian inference with a fully connected neural network is solvable. We provide techniques to compute the model evidence and posterior to arbitrary order in $1/N$ and at arbitrary temperature.
  arXiv  Detail & Related papers  (2024-05-26T17:08:04Z)
• Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks [54.177130905659155]
  Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks. In this paper, we study a suitable function space for over- parameterized two-layer neural networks with bounded norms.
  arXiv  Detail & Related papers  (2024-04-29T15:04:07Z)
• Gauss-Newton Temporal Difference Learning with Nonlinear Function Approximation [11.925232472331494]
  A Gauss-Newton Temporal Difference (GNTD) learning method is proposed to solve the Q-learning problem with nonlinear function approximation. In each iteration, our method takes one Gauss-Newton (GN) step to optimize a variant of Mean-Squared Bellman Error (MSBE) We validate our method via extensive experiments in several RL benchmarks, where GNTD exhibits both higher rewards and faster convergence than TD-type methods.
  arXiv  Detail & Related papers  (2023-02-25T14:14:01Z)
• Neural Networks Efficiently Learn Low-Dimensional Representations with SGD [22.703825902761405]
  We show that SGD-trained ReLU NNs can learn a single-index target of the form $y=f(langleboldsymbolu,boldsymbolxrangle) + epsilon$ by recovering the principal direction. We also provide compress guarantees for NNs using the approximate low-rank structure produced by SGD.
  arXiv  Detail & Related papers  (2022-09-29T15:29:10Z)
• Bounding the Width of Neural Networks via Coupled Initialization -- A Worst Case Analysis [121.9821494461427]
  We show how to significantly reduce the number of neurons required for two-layer ReLU networks. We also prove new lower bounds that improve upon prior work, and that under certain assumptions, are best possible.
  arXiv  Detail & Related papers  (2022-06-26T06:51:31Z)
• Feature Learning in $L_{2}$-regularized DNNs: Attraction/Repulsion and Sparsity [9.077741848403791]
  We show that the loss in terms of the parameters can be reformulated into a loss in terms of the layerwise activations $Z_ell$ of the training set. This reformulation reveals the dynamics behind feature learning.
  arXiv  Detail & Related papers  (2022-05-31T14:10:15Z)
• High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation [89.21686761957383]
  We study the first gradient descent step on the first-layer parameters $boldsymbolW$ in a two-layer network. Our results demonstrate that even one step can lead to a considerable advantage over random features.
  arXiv  Detail & Related papers  (2022-05-03T12:09:59Z)
• 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)
• Large-time asymptotics in deep learning [0.0]
  We consider the impact of the final time $T$ (which may indicate the depth of a corresponding ResNet) in training. For the classical $L2$--regularized empirical risk minimization problem, we show that the training error is at most of the order $mathcalOleft(frac1Tright)$. In the setting of $ellp$--distance losses, we prove that both the training error and the optimal parameters are at most of the order $mathcalOleft(e-mu
  arXiv  Detail & Related papers  (2020-08-06T07:33:17Z)

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.