Neural Functional: Learning Function to Scalar Maps for Neural PDE Surrogates

• URL: http://arxiv.org/abs/2505.13275v1
• Date: Mon, 19 May 2025 15:55:38 GMT
• Title: Neural Functional: Learning Function to Scalar Maps for Neural PDE Surrogates
• Abstract summary: We propose a new architecture for PDE surrogates that learns function to scalar mappings.<n>For the first time, this allows for an extension of Hamiltonian mechanics to neural PDE surrogates.
• Score: 7.136205674624813
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Many architectures for neural PDE surrogates have been proposed in recent years, largely based on neural networks or operator learning. In this work, we derive and propose a new architecture, the Neural Functional, which learns function to scalar mappings. Its implementation leverages insights from operator learning and neural fields, and we show the ability of neural functionals to implicitly learn functional derivatives. For the first time, this allows for an extension of Hamiltonian mechanics to neural PDE surrogates by learning the Hamiltonian functional and optimizing its functional derivatives. We demonstrate that the Hamiltonian Neural Functional can be an effective surrogate model through improved stability and conserving energy-like quantities on 1D and 2D PDEs. Beyond PDEs, functionals are prevalent in physics; functional approximation and learning with its gradients may find other uses, such as in molecular dynamics or design optimization.

Related papers

• Kolmogorov-Arnold Representation for Symplectic Learning: Advancing Hamiltonian Neural Networks [4.130455471816662]
  Hamiltonian Neural Networks (HNNs) ensure energy conservation by learning Hamiltonian functions directly from data.<n>Our approach exploits localized function approximations to better capture high-frequency and multi-scale dynamics.<n>The networks preserve the symplectic form of Hamiltonian systems, and thus maintain interpretability and physical consistency.
  arXiv  Detail & Related papers  (2025-08-26T20:22:33Z)
• Principled Approaches for Extending Neural Architectures to Function Spaces for Operator Learning [78.88684753303794]
  Deep learning has predominantly advanced through applications in computer vision and natural language processing.<n>Neural operators are a principled way to generalize neural networks to mappings between function spaces.<n>This paper identifies and distills the key principles for constructing practical implementations of mappings between infinite-dimensional function spaces.
  arXiv  Detail & Related papers  (2025-06-12T17:59:31Z)
• Energy-Embedded Neural Solvers for One-Dimensional Quantum Systems [4.804387866232918]
  We propose an energy-embedding-based physics-informed neural network method for solving the Schr"odinger equation.<n>The proposed approach can be extended to solve other partial differential equations beyond the Schr"odinger equation.
  arXiv  Detail & Related papers  (2025-05-30T04:13:26Z)
• DimOL: Dimensional Awareness as A New 'Dimension' in Operator Learning [60.58067866537143]
  We introduce DimOL (Dimension-aware Operator Learning), drawing insights from dimensional analysis.<n>To implement DimOL, we propose the ProdLayer, which can be seamlessly integrated into FNO-based and Transformer-based PDE solvers.<n> Empirically, DimOL models achieve up to 48% performance gain within the PDE datasets.
  arXiv  Detail & Related papers  (2024-10-08T10:48:50Z)
• Learning Generalized Hamiltonians using fully Symplectic Mappings [0.32985979395737786]
  Hamiltonian systems have the important property of being conservative, that is, energy is conserved throughout the evolution.<n>In particular Hamiltonian Neural Networks have emerged as a mechanism to incorporate structural inductive bias into the NN model.<n>We show that symplectic schemes are robust to noise and provide a good approximation of the system Hamiltonian when the state variables are sampled from a noisy observation.
  arXiv  Detail & Related papers  (2024-09-17T12:45:49Z)
• Neural Pfaffians: Solving Many Many-Electron Schrödinger Equations [58.130170155147205]
  Neural wave functions accomplished unprecedented accuracies in approximating the ground state of many-electron systems, though at a high computational cost. Recent works proposed amortizing the cost by learning generalized wave functions across different structures and compounds instead of solving each problem independently. This work tackles the problem by defining overparametrized, fully learnable neural wave functions suitable for generalization across molecules.
  arXiv  Detail & Related papers  (2024-05-23T16:30:51Z)
• Efficient explicit gate construction of block-encoding for Hamiltonians needed for simulating partial differential equations [0.6144680854063939]
  One of the most promising applications of quantum computers is solving partial differential equations (PDEs)<n>By using the Schrodingerisation technique - which converts non-conservative PDEs into Schrodinger equations - the problem can be reduced to Hamiltonian simulations.<n>This paper addresses an important gap by efficiently loading these Hamiltonians into the quantum computer through block-encoding.
  arXiv  Detail & Related papers  (2024-05-21T15:13:02Z)
• Approximation of RKHS Functionals by Neural Networks [30.42446856477086]
  We study the approximation of functionals on kernel reproducing Hilbert spaces (RKHS's) using neural networks. We derive explicit error bounds for those induced by inverse multiquadric, Gaussian, and Sobolev kernels. We apply our findings to functional regression, proving that neural networks can accurately approximate the regression maps.
  arXiv  Detail & Related papers  (2024-03-18T18:58:23Z)
• Efficient and Flexible Neural Network Training through Layer-wise Feedback Propagation [49.44309457870649]
  Layer-wise Feedback feedback (LFP) is a novel training principle for neural network-like predictors.<n>LFP decomposes a reward to individual neurons based on their respective contributions.<n>Our method then implements a greedy reinforcing approach helpful parts of the network and weakening harmful ones.
  arXiv  Detail & Related papers  (2023-08-23T10:48:28Z)
• Embedding Capabilities of Neural ODEs [0.0]
  We study input-output relations of neural ODEs using dynamical systems theory. We prove several results about the exact embedding of maps in different neural ODE architectures in low and high dimension.
  arXiv  Detail & Related papers  (2023-08-02T15:16:34Z)
• Learning Neural Constitutive Laws From Motion Observations for Generalizable PDE Dynamics [97.38308257547186]
  Many NN approaches learn an end-to-end model that implicitly models both the governing PDE and material models. We argue that the governing PDEs are often well-known and should be explicitly enforced rather than learned. We introduce a new framework termed "Neural Constitutive Laws" (NCLaw) which utilizes a network architecture that strictly guarantees standard priors.
  arXiv  Detail & Related papers  (2023-04-27T17:42:24Z)
• Neural Operator: Learning Maps Between Function Spaces [75.93843876663128]
  We propose a generalization of neural networks to learn operators, termed neural operators, that map between infinite dimensional function spaces. We prove a universal approximation theorem for our proposed neural operator, showing that it can approximate any given nonlinear continuous operator. An important application for neural operators is learning surrogate maps for the solution operators of partial differential equations.
  arXiv  Detail & Related papers  (2021-08-19T03:56:49Z)
• Nuclei with up to $\oldsymbol{A=6}$ nucleons with artificial neural network wave functions [52.77024349608834]
  We use artificial neural networks to compactly represent the wave functions of nuclei. We benchmark their binding energies, point-nucleon densities, and radii with the highly accurate hyperspherical harmonics method.
  arXiv  Detail & Related papers  (2021-08-15T23:02:39Z)
• Going Beyond Linear RL: Sample Efficient Neural Function Approximation [76.57464214864756]
  We study function approximation with two-layer neural networks. Our results significantly improve upon what can be attained with linear (or eluder dimension) methods.
  arXiv  Detail & Related papers  (2021-07-14T03:03:56Z)
• Non-linear Functional Modeling using Neural Networks [6.624726878647541]
  We introduce a new class of non-linear models for functional data based on neural networks. We propose two variations of our framework: a functional neural network with continuous hidden layers, and a second version that utilizes basis expansions and continuous hidden layers.
  arXiv  Detail & Related papers  (2021-04-19T14:59:55Z)
• Fourier Neural Operator for Parametric Partial Differential Equations [57.90284928158383]
  We formulate a new neural operator by parameterizing the integral kernel directly in Fourier space. We perform experiments on Burgers' equation, Darcy flow, and Navier-Stokes equation. It is up to three orders of magnitude faster compared to traditional PDE solvers.
  arXiv  Detail & Related papers  (2020-10-18T00:34:21Z)
• Variational Monte Carlo calculations of $\mathbf{A\leq 4}$ nuclei with an artificial neural-network correlator ansatz [62.997667081978825]
  We introduce a neural-network quantum state ansatz to model the ground-state wave function of light nuclei. We compute the binding energies and point-nucleon densities of $Aleq 4$ nuclei as emerging from a leading-order pionless effective field theory Hamiltonian.
  arXiv  Detail & Related papers  (2020-07-28T14:52:28Z)
• Method of spectral Green functions in driven open quantum dynamics [77.34726150561087]
  A novel method based on spectral Green functions is presented for the simulation of driven open quantum dynamics. The formalism shows remarkable analogies to the use of Green functions in quantum field theory. The method dramatically reduces computational cost compared with simulations based on solving the full master equation.
  arXiv  Detail & Related papers  (2020-06-04T09:41:08Z)
• Recurrent Neural Network Wave Functions [0.36748639131154304]
  A core technology that has emerged from the artificial intelligence revolution is the recurrent neural network (RNN) We demonstrate the effectiveness of RNN wave functions by calculating ground state energies, correlation functions, and entanglement entropies for several quantum spin models of interest to condensed matter physicists.
  arXiv  Detail & Related papers  (2020-02-07T19:00:03Z)

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.