---
title: "Variational Functional Neural Networks (vfNN)"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.03542v1"
permalink: "https://feed.astralor.com/items/itm_06c3919d5a08f34e38b7cfd5"
published: "2026-11-02T18:04:46.000Z"
score: 57
channel: "ai"
tags: ["Variational Functional Neural","Networks","Lagrangian","Hamiltonian","Euler-Lagrange"]
---

# Variational Functional Neural Networks (vfNN)

## 速览

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 syst…

## 关键点

- 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 syst…
- That way, vfNN bypasses solving the equations of motion (a.k.a.
- the Euler-Lagrange equations), which are in the form of differential equations.

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_06c3919d5a08f34e38b7cfd5