English
Related papers

Related papers: Exact conservation laws for neural network integra…

200 papers

We consider the calculation of Euler--Lagrange systems of ordinary difference equations, including the difference Noether's Theorem, in the light of the recently-developed calculus of difference invariants and discrete moving frames. We…

Numerical Analysis · Mathematics 2021-06-01 E. L. Mansfield , A. Rojo-Echeburua , L. Peng , P. E. Hydon

A didatic approach of the Noether's theorem in classical mechanics is derived and used to obtain the laws of conservation.

Classical Physics · Physics 2007-05-23 Rubens de Melo Marinho

We will read, through the Emmy Noether paper and the two concepts of `proper' and `improper' conservation laws, the problem, posed by Hilbert, of the nature of the law of conservation of energy in the theory of General Relativity.…

History and Philosophy of Physics · Physics 2021-01-06 M. Palese , E. Winterroth

Noether's First Theorem yields conservation laws for Lagrangians with a variational symmetry group. The explicit formulae for the laws are well known and the symmetry group is known to act on the linear space generated by the conservation…

Differential Geometry · Mathematics 2013-02-18 Tania M. N. Goncalves , Elizabeth L. Mansfield

In nature, symmetry governs regularities, while symmetry breaking brings texture. In artificial neural networks, symmetry has been a central design principle to efficiently capture regularities in the world, but the role of symmetry…

Machine Learning · Computer Science 2021-11-03 Hidenori Tanaka , Daniel Kunin

Noether's first and second theorems both imply conserved currents that can be identified as an energy-momentum tensor (EMT). The first theorem identifies the EMT as the conserved current associated with global spacetime translations, while…

High Energy Physics - Theory · Physics 2026-01-16 Adam Freese

A number of optimization algorithms have been inspired by the physics of Newtonian motion. Here, we ask the question: do algorithms themselves obey some ``natural laws of motion,'' and can they be derived by an application of these laws? We…

Optimization and Control · Mathematics 2026-04-21 I. M. Ross

We prove that under certain assumptions a partial differential equation can be derived from a variational principle. It is well-known from Noether's theorem that symmetries of a variational functional lead to conservation laws of the…

Differential Geometry · Mathematics 2019-10-07 Markus Dafinger

Divergence-free symmetric tensors (DFSTs) are fundamental in continuum mechanics, encoding conservation laws such as mass and momentum conservation. We introduce Riemann Tensor Neural Networks (RTNNs), a novel neural architecture that…

Machine Learning · Computer Science 2025-06-17 Anas Jnini , Lorenzo Breschi , Flavio Vella

The direct method based on the definition of conserved currents of a system of differential equations is applied to compute the space of conservation laws of the (1+1)-dimensional wave equation in the light-cone coordinates. Then Noether's…

Analysis of PDEs · Mathematics 2020-01-23 Roman O. Popovych , Alexei F. Cheviakov

We consider the problem of designing almost optimal predictors for dynamical systems from a finite sequence of noisy observations and incomplete knowledge of the dynamics and the noise. We first discuss the properties of the optimal (Bayes)…

Chaotic Dynamics · Physics 2007-07-30 Marian Anghel , Ingo Steinwart

Conservation laws in ideal gas dynamics and magnetohydrodynamics (MHD) associated with fluid relabelling symmetries are derived using Noether's first and second theorems. Lie dragged invariants are discussed in terms of the MHD Casimirs. A…

Mathematical Physics · Physics 2014-03-05 G. M. Webb , B. Dasgupta , J. F. McKenzie , Q. Hu , G. P. Zank

Many complex physical systems admit natural decomposition into an exactly solvable component and a perturbative correction. Rather than training neural networks to learn complete trajectories from scratch, we introduce Neural Network…

Computational Physics · Physics 2025-12-02 Zhenhao Chen , Mutian Shen , Boris Fain , Zohar Nussinov

It is shown that the Kadanoff-Baym equations at consistent first-order gradient approximation reveal exact rather than approximate conservation laws related to global symmetries of the system. The conserved currents and energy-momentum…

Nuclear Theory · Physics 2011-08-12 J. Knoll , Yu. B. Ivanov , D. N. Voskresensky

When learning dynamical systems from data, embedding physical structure can constrain the solution space and improve generalization, but many physics-informed models assume access to the full system state. This limits their use in partially…

Machine Learning · Computer Science 2026-05-25 Sunniva Meltzer , Sølve Eidnes , Alexander Johannes Stasik

The Noether theorem for Hamiltonian constrained systems is revisited. In particular, our review presents a novel method to show that the gauge transformations are generated by the conserved quantities associated with the first class…

High Energy Physics - Theory · Physics 2009-11-11 V. M. Villanueva , J. A. Nieto , L. Ruiz , J. Silvas

We present an algorithm to learn the relevant latent variables of a large-scale discretized physical system and predict its time evolution using thermodynamically-consistent deep neural networks. Our method relies on sparse autoencoders,…

Computational Engineering, Finance, and Science · Computer Science 2021-03-25 Quercus Hernandez , Alberto Badias , David Gonzalez , Francisco Chinesta , Elias Cueto

We examine the assumptions behind Noether's theorem connecting symmetries and conservation laws. To compare classical and quantum versions of this theorem, we take an algebraic approach. In both classical and quantum mechanics, observables…

Mathematical Physics · Physics 2025-11-04 John C. Baez

Neural ordinary differential equations (ODEs) have attracted much attention as continuous-time counterparts of deep residual neural networks (NNs), and numerous extensions for recurrent NNs have been proposed. Since the 1980s, ODEs have…

Machine Learning · Computer Science 2022-10-17 Kazuki Irie , Francesco Faccio , Jürgen Schmidhuber

Identification of a linear time-invariant dynamical system from partial observations is a fundamental problem in control theory. Particularly challenging are systems exhibiting long-term memory. A natural question is how learn such systems…

Machine Learning · Computer Science 2022-03-08 Holden Lee