English
Related papers

Related papers: Newton's algorithm for discrete classical dynamics

200 papers

Viewing optimization methods as numerical integrators for ordinary differential equations (ODEs) provides a thought-provoking modern framework for studying accelerated first-order optimizers. In this literature, acceleration is often…

Optimization and Control · Mathematics 2021-02-24 Peiyuan Zhang , Antonio Orvieto , Hadi Daneshmand , Thomas Hofmann , Roy Smith

Emergent phenomena share the fascinating property of not being obvious consequences of the design of the system in which they appear. This characteristic is no less relevant when attempting to simulate such phenomena, given that the outcome…

Soft Condensed Matter · Physics 2014-11-26 D. C. Rapaport

We introduce a unified framework -- Quantum Neural Ordinary and Partial Differential Equations (QNODEs and QNPDEs) -- which extends the continuous-time formalism of classical neural ordinary and partial differential equations into quantum…

Quantum Physics · Physics 2026-01-13 Yu Cao , Shi Jin , Nana Liu

Molecular dynamics (MD) simulations employing classical force fields constitute the cornerstone of contemporary atomistic modeling in chemistry, biology, and materials science. However, the predictive power of these simulations is only as…

Chemical Physics · Physics 2018-09-26 Stefan Chmiela , Huziel E. Sauceda , Klaus-Robert Müller , Alexandre Tkatchenko

The traditional Newton method for solving nonlinear operator equations in Banach spaces is discussed within the context of the continuous Newton method. This setting makes it possible to interpret the Newton method as a discrete dynamical…

Numerical Analysis · Mathematics 2016-07-13 Mario Amrein , Thomas P. Wihler

General molecular dynamic approach, making possible direct calculation of eigen values and eigen functions for a quantum-mechanical system of an arbitrary symmetry is proposed. The method is based on analogy between discrete representation…

Disordered Systems and Neural Networks · Physics 2007-05-23 V. N. Pyrkov , V. M. Burlakov

Action at distance in Newtonian physics is replaced by finite propagation speeds in classical post--Newtonian physics. As a result, the differential equations of motion in Newtonian physics are replaced by functional differential equations,…

General Physics · Physics 2011-08-31 Jaume Giné

We have proposed a method for the dynamic simulation of a collection of self-propelled particles in a viscous Newtonian fluid. We restrict attention to particles whose size and velocity are small enough that the fluid motion is in the…

Soft Condensed Matter · Physics 2015-05-13 Vishwajeet Mehandia , Prabhu R. Nott

We highlight a formal and substantial analogy between Machine Learning (ML) algorithms and discrete dynamical systems (DDS) in relaxation form. The analogy offers a transparent interpretation of the weights in terms of physical…

Machine Learning · Computer Science 2025-09-10 Sauro Succi

Symmetry-preserving (mimetic) discretization aims to preserve certain properties of a continuous differential operator in its discrete counterpart. For these discretizations, stability and (discrete) conservation of mass, momentum and…

Numerical Analysis · Mathematics 2019-05-13 Bas van 't Hof , Mathea J. Vuik

Even for the gradient descent (GD) method applied to neural network training, understanding its optimization dynamics, including convergence rate, iterate trajectories, function value oscillations, and especially its implicit acceleration,…

Machine Learning · Computer Science 2026-05-22 Alexander Tyurin

Recent progress in the development of quantum technologies has enabled the direct investigation of dynamics of increasingly complex quantum many-body systems. This motivates the study of the complexity of classical algorithms for this…

Quantum Physics · Physics 2023-07-12 Dominik S. Wild , Álvaro M. Alhambra

We discuss a role of a momentum vector in the description of dynamics of systems with variable mass, and show some ambiguity in expressing the 2nd Newtonian law of dynamics in terms of momentum change in time for variable-mass systems. A…

Classical Physics · Physics 2019-06-20 Janusz Wolny , Radoslaw Strzalka

The Newton method is a powerful optimization algorithm, valued for its rapid local convergence and elegant geometric properties. However, its theoretical guarantees are usually limited to convex problems. In this work, we ask whether…

Optimization and Control · Mathematics 2025-10-01 Alexander Shestakov , Sushil Bohara , Samuel Horváth , Martin Takáč , Slavomír Hanzely

We report a new deep learning message passing network that takes inspiration from Newton's equations of motion to learn interatomic potentials and forces. With the advantage of directional information from trainable latent force vectors,…

In a Hilbert setting, we introduce a new dynamical system and associated algorithms for solving monotone inclusions by rapid methods. Given a maximal monotone operator $A$, the evolution is governed by the time dependent operator $I -(I +…

Optimization and Control · Mathematics 2015-04-20 Hedy Attouch , Maicon Marques Alves , Benar F. Svaiter

Sometimes it is necessary to obtain a numerical integration using only discretised data. In some cases, the data contains singularities which position is known but does not coincide with a discretisation point, and the jumps in the function…

Numerical Analysis · Mathematics 2022-09-09 Sergio Amat , Zhilin Li , Juan Ruiz-Alvarez , Concepcion Solano , Juan C. Trillo

Discovering constants of motion is meaningful in helping understand the dynamical systems, but inevitably needs proficient mathematical skills and keen analytical capabilities. With the prevalence of deep learning, methods employing neural…

Machine Learning · Computer Science 2025-04-15 Wenqi Fang , Chao Chen , Yongkui Yang , Zheng Wang

We analyze the convergence rate of various momentum-based optimization algorithms from a dynamical systems point of view. Our analysis exploits fundamental topological properties, such as the continuous dependence of iterates on their…

Optimization and Control · Mathematics 2021-04-13 Michael Muehlebach , Michael I. Jordan

We study the asymptotic behavior of second-order algorithms mixing Newton's method and inertial gradient descent in non-convex landscapes. We show that, despite the Newtonian behavior of these methods, they almost always escape strict…

Optimization and Control · Mathematics 2024-02-13 Camille Castera