English
Related papers

Related papers: Keep the Momentum: Conservation Laws beyond Euclid…

200 papers

While conservation laws in gradient flow training dynamics are well understood for (mostly shallow) ReLU and linear networks, their study remains largely unexplored for more practical architectures. This paper bridges this gap by deriving…

Machine Learning · Computer Science 2025-06-09 Sibylle Marcotte , Rémi Gribonval , Gabriel Peyré

Understanding the geometric properties of gradient descent dynamics is a key ingredient in deciphering the recent success of very large machine learning models. A striking observation is that trained over-parameterized models retain some…

Machine Learning · Computer Science 2024-07-11 Sibylle Marcotte , Rémi Gribonval , Gabriel Peyré

Why does gradient descent reliably find good solutions in non-convex neural network optimization, despite the landscape being NP-hard in the worst case? We show that gradient flow on L-layer ReLU networks without bias preserves L-1…

Machine Learning · Computer Science 2026-04-10 Daniel Nobrega Medeiros

All low-order conservation laws are found for a general class of nonlinear wave equations in one dimension with linear damping which is allowed to be time-dependent. Such equations arise in numerous physical applications and have attracted…

Mathematical Physics · Physics 2025-10-20 Stephen C. Anco , Almudena P. Marquez , Tamara M. Garrido , Maria L. Gandarias

In an earlier work by a subset of the present authors, the method of the so-called neural deflation was introduced towards identifying a complete set of functionally independent conservation laws of a nonlinear dynamical system. Here, we…

Pattern Formation and Solitons · Physics 2024-10-10 Shaoxuan Chen , Panayotis G. Kevrekidis , Hong-Kun Zhang , Wei Zhu

Conservation principles are essential to describe and quantify dynamical processes in all areas of physics. Classically, a conservation law holds because the description of reality can be considered independent of an observation…

Quantum Physics · Physics 2021-03-24 Stanisław Sołtan , Mateusz Frączak , Wolfgang Belzig , Adam Bednorz

The paper is concerned with a scalar conservation law with discontinuous gradient-dependent flux. Namely, the flux is described by two different functions $f(u)$ or $g(u)$, when the gradient $u_x$ of the solution is positive or negative,…

Analysis of PDEs · Mathematics 2026-01-26 Debora Amadori , Alberto Bressan , Wen Shen

Conservation laws are of great theoretical and practical interest. We describe a novel approach to machine learning conservation laws of finite-dimensional dynamical systems using trajectory data. It is the first such approach based on…

Computational Physics · Physics 2024-06-03 Meskerem Abebaw Mebratie , Rüdiger Nather , Guido Falk von Rudorff , Werner M. Seiler

Conservation laws are an inherent feature in many systems modeling real world phenomena, in particular, those modeling biological and chemical systems. If the form of the underlying dynamical system is known, linear algebra and algebraic…

Numerical Analysis · Mathematics 2024-03-11 Tracey Oellerich , Maria Emelianenko

The paper is concerned with a scalar conservation law with discontinuous gradient-dependent flux. Namely, the flux is described by two different functions $f(u)$ or $g(u)$, when the gradient $u_x$ of the solution is positive or negative,…

Analysis of PDEs · Mathematics 2024-11-18 Debora Amadori , Alberto Bressan , Wen Shen

The conditions of existence of extra mass flux in single component dissipative non-relativistic fluids are clarified. By considering Galilean invariance we show that if total mass flux is equal to total momentum density, then mass,…

Fluid Dynamics · Physics 2017-04-11 Peter Ván , Michal Pavelka , Miroslav Grmela

In this work we present a nonlocal conservation law with a velocity depending on an integral term over a part of the space. The model class covers already existing models in literature, but it is also able to describe new dynamics mainly…

Analysis of PDEs · Mathematics 2023-04-25 Jan Friedrich , Simone Göttlich , Alexander Keimer , Lukas Pflug

The study rederives the fundamental equations of fluid flow and examines the inherent relationship between momentum conservation and mechanical energy conservation. It is shown that the material derivative of velocity is to depict the…

Fluid Dynamics · Physics 2023-12-07 Peng Shi

We present a novel method for guaranteeing linear momentum in learned physics simulations. Unlike existing methods, we enforce conservation of momentum with a hard constraint, which we realize via antisymmetrical continuous convolutional…

Machine Learning · Computer Science 2022-11-03 Lukas Prantl , Benjamin Ummenhofer , Vladlen Koltun , Nils Thuerey

A modular fluid-flow model for network congestion analysis and control is proposed. The model is derived from an information conservation law stating that the information is either in transit, lost or received. Mathematical models of…

Networking and Internet Architecture · Computer Science 2012-08-07 Corentin Briat , Emre Altug Yavuz , Gunnar Karlsson

The momentum conservation law for general dissipationless reduced-fluid (e.g., gyrofluid) models is derived by Noether method from a variational principle. The reduced-fluid momentum density and the reduced-fluid canonical momentum-stress…

Plasma Physics · Physics 2010-09-17 Alain J. Brizard

The solution of time dependent differential equations with neural networks has attracted a lot of attention recently. The central idea is to learn the laws that govern the evolution of the solution from data, which might be polluted with…

Dynamical Systems · Mathematics 2023-06-14 Eike Hermann Müller

Reduced order models of nonlinear conservation laws in fluid dynamics do not typically inherit stability properties of the full order model. We introduce projection-based hyper-reduced models of nonlinear conservation laws which are…

Numerical Analysis · Mathematics 2020-10-28 Jesse Chan

Conservation laws are the pillars of physics. It's what we held on to when our imagination was challenged during the days of relativity or quantum mechanics. Their violation leads to the most absurd models, so excellently exercised in the…

Biological Physics · Physics 2020-04-23 Matthias Ferdinand Schneider

We introduce a methodology for seeking conservation laws within a Hamiltonian dynamical system, which we term ``neural deflation''. Inspired by deflation methods for steady states of dynamical systems, we propose to {iteratively} train a…

Pattern Formation and Solitons · Physics 2023-03-29 Wei Zhu , Hong-Kun Zhang , P. G. Kevrekidis
‹ Prev 1 2 3 10 Next ›