Weight-Parameterization in Continuous Time Deep Neural Networks for Surrogate Modeling

• URL: http://arxiv.org/abs/2507.22045v1
• Date: Tue, 29 Jul 2025 17:49:43 GMT
• Title: Weight-Parameterization in Continuous Time Deep Neural Networks for Surrogate Modeling
• Authors: Haley Rosso, Lars Ruthotto, Khachik Sargsyan,
• Abstract summary: Continuous-time deep learning models, such as neural ordinary differential equations (ODEs), offer a promising framework for surrogate modeling of complex physical systems.<n>A central challenge in training these models lies in learning yet stable time-varying weights, particularly under computational constraints.<n>This work investigates weight parameterization strategies that constrain temporal evolution of weights to a low-dimensional subspace spanned by basis functions.
• Score: 1.629803445577911
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Continuous-time deep learning models, such as neural ordinary differential equations (ODEs), offer a promising framework for surrogate modeling of complex physical systems. A central challenge in training these models lies in learning expressive yet stable time-varying weights, particularly under computational constraints. This work investigates weight parameterization strategies that constrain the temporal evolution of weights to a low-dimensional subspace spanned by polynomial basis functions. We evaluate both monomial and Legendre polynomial bases within neural ODE and residual network (ResNet) architectures under discretize-then-optimize and optimize-then-discretize training paradigms. Experimental results across three high-dimensional benchmark problems show that Legendre parameterizations yield more stable training dynamics, reduce computational cost, and achieve accuracy comparable to or better than both monomial parameterizations and unconstrained weight models. These findings elucidate the role of basis choice in time-dependent weight parameterization and demonstrate that using orthogonal polynomial bases offers a favorable tradeoff between model expressivity and training efficiency.

Related papers

• Neural Port-Hamiltonian Differential Algebraic Equations for Compositional Learning of Electrical Networks [20.12750360095627]
  We develop compositional learning algorithms for coupled dynamical systems.<n>We use neural networks to parametrize unknown terms in differential and algebraic components of a port-Hamiltonian DAE.<n>We train individual N-PHDAE models for separate grid components, before coupling them to accurately predict the behavior of larger-scale networks.
  arXiv  Detail & Related papers  (2024-12-15T15:13:11Z)
• A parametric framework for kernel-based dynamic mode decomposition using deep learning [0.0]
  The proposed framework consists of two stages, offline and online. The online stage leverages those LANDO models to generate new data at a desired time instant. dimensionality reduction technique is applied to high-dimensional dynamical systems to reduce the computational cost of training.
  arXiv  Detail & Related papers  (2024-09-25T11:13:50Z)
• Physics-informed Discretization-independent Deep Compositional Operator Network [1.2430809884830318]
  We introduce a novel physics-informed model architecture which can generalize to various discrete representations of PDE parameters and irregular domain shapes. Inspired by deep operator neural networks, our model involves a discretization-independent learning of parameter embedding repeatedly. Numerical results demonstrate the accuracy and efficiency of the proposed method.
  arXiv  Detail & Related papers  (2024-04-21T12:41:30Z)
• Data-free Weight Compress and Denoise for Large Language Models [96.68582094536032]
  We propose a novel approach termed Data-free Joint Rank-k Approximation for compressing the parameter matrices.<n>We achieve a model pruning of 80% parameters while retaining 93.43% of the original performance without any calibration data.
  arXiv  Detail & Related papers  (2024-02-26T05:51:47Z)
• Discovering Interpretable Physical Models using Symbolic Regression and Discrete Exterior Calculus [55.2480439325792]
  We propose a framework that combines Symbolic Regression (SR) and Discrete Exterior Calculus (DEC) for the automated discovery of physical models. DEC provides building blocks for the discrete analogue of field theories, which are beyond the state-of-the-art applications of SR to physical problems. We prove the effectiveness of our methodology by re-discovering three models of Continuum Physics from synthetic experimental data.
  arXiv  Detail & Related papers  (2023-10-10T13:23:05Z)
• Active-Learning-Driven Surrogate Modeling for Efficient Simulation of Parametric Nonlinear Systems [0.0]
  In absence of governing equations, we need to construct the parametric reduced-order surrogate model in a non-intrusive fashion. Our work provides a non-intrusive optimality criterion to efficiently populate the parameter snapshots. We propose an active-learning-driven surrogate model using kernel-based shallow neural networks.
  arXiv  Detail & Related papers  (2023-06-09T18:01:14Z)
• Capturing dynamical correlations using implicit neural representations [85.66456606776552]
  We develop an artificial intelligence framework which combines a neural network trained to mimic simulated data from a model Hamiltonian with automatic differentiation to recover unknown parameters from experimental data. In doing so, we illustrate the ability to build and train a differentiable model only once, which then can be applied in real-time to multi-dimensional scattering data.
  arXiv  Detail & Related papers  (2023-04-08T07:55:36Z)
• Generalized Neural Closure Models with Interpretability [28.269731698116257]
  We develop a novel and versatile methodology of unified neural partial delay differential equations. We augment existing/low-fidelity dynamical models directly in their partial differential equation (PDE) forms with both Markovian and non-Markovian neural network (NN) closure parameterizations. We demonstrate the new generalized neural closure models (gnCMs) framework using four sets of experiments based on advecting nonlinear waves, shocks, and ocean acidification models.
  arXiv  Detail & Related papers  (2023-01-15T21:57:43Z)
• On the Influence of Enforcing Model Identifiability on Learning dynamics of Gaussian Mixture Models [14.759688428864159]
  We propose a technique for extracting submodels from singular models. Our method enforces model identifiability during training. We show how the method can be applied to more complex models like deep neural networks.
  arXiv  Detail & Related papers  (2022-06-17T07:50:22Z)
• 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)
• Equivariant vector field network for many-body system modeling [65.22203086172019]
  Equivariant Vector Field Network (EVFN) is built on a novel equivariant basis and the associated scalarization and vectorization layers. We evaluate our method on predicting trajectories of simulated Newton mechanics systems with both full and partially observed data.
  arXiv  Detail & Related papers  (2021-10-26T14:26:25Z)
• Large-scale Neural Solvers for Partial Differential Equations [48.7576911714538]
  Solving partial differential equations (PDE) is an indispensable part of many branches of science as many processes can be modelled in terms of PDEs. Recent numerical solvers require manual discretization of the underlying equation as well as sophisticated, tailored code for distributed computing. We examine the applicability of continuous, mesh-free neural solvers for partial differential equations, physics-informed neural networks (PINNs) We discuss the accuracy of GatedPINN with respect to analytical solutions -- as well as state-of-the-art numerical solvers, such as spectral solvers.
  arXiv  Detail & Related papers  (2020-09-08T13:26:51Z)

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.