Variational Functional Neural Networks (vfNN)
Abstract
We present a variational functional neural network (vfNN) algorithm that optimizes physically motivated continuum functionals in integral form (e.g., Lagrangian, Hamiltonian, or free energy) to find the states of a system. That way, vfNN bypasses solving the equations of motion (a.k.a. the Euler-Lagrange equations), which are in the form of differential equations. To this end, our approach is fundamentally different from conventional physics-informed neural networks (PINN) that solve differential equations by minimizing a phenomenological loss function involving higher order derivatives and ad hoc weight factors. In contrast, vfNN merely evaluates lower order derivatives of the generating functional and replaces the weight factors with rigorous physical scales. This also fundamentally changes the loss landscape, and the desired solutions may become unstable. For this emergent nonconvex optimization problem, we develop a quasi-Newton optimization algorithm with simulated annealing that converges to the solutions of the corresponding Euler-Lagrange equations of the functional regardless of their stability properties. Our simulations using vfNN give accurate results for benchmark systems governed by linear or nonlinear ordinary differential equations.
Related
- End-to-End Quantum Semantic Communication with Variational Quantum Neural Networks
- Compact Variational Neural Networks for Spectral Inference from a Single Nonlinear 2D Perovskite Photodetector
- Neural-Network-Based Variational Method in Nuclear Density Functional Theory: Application to the Kohn--Sham method
- Utilizing Neural Networks for Solving Functional Renormalization Group Flow Equations
- Nonperturbative functional renormalization group for Higgs-singlet models with physics-informed neural networks
BibTeX
@misc{katke2026variational,
title = {{Variational Functional Neural Networks (vfNN)}},
author = {Chinmay Katke and C. Nadir Kaplan},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.03542},
eprint = {2611.03542},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.03542},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Variational Functional Neural Networks (vfNN)
AU - Chinmay Katke
AU - C. Nadir Kaplan
PY - 2026
DA - 2026/11/02
PB - arXiv
DO - 10.48550/arxiv.2611.03542
UR - https://arxiv.org/abs/2611.03542
AB - We present a variational functional neural network (vfNN) algorithm that optimizes physically motivated continuum functionals in integral form (e.g., Lagrangian, Hamiltonian, or free energy) to find the states of a system. That way, vfNN bypasses solving the equations of motion (a.k.a. the Euler-Lagrange equations), which are in the form of differential equations. To this end, our approach is fundamentally different from conventional physics-informed neural networks (PINN) that solve differential equations by minimizing a phenomenological loss function involving higher order derivatives and ad hoc weight factors. In contrast, vfNN merely evaluates lower order derivatives of the generating functional and replaces the weight factors with rigorous physical scales. This also fundamentally changes the loss landscape, and the desired solutions may become unstable. For this emergent nonconvex optimization problem, we develop a quasi-Newton optimization algorithm with simulated annealing that converges to the solutions of the corresponding Euler-Lagrange equations of the functional regardless of their stability properties. Our simulations using vfNN give accurate results for benchmark systems governed by linear or nonlinear ordinary differential equations.
ER -