English
Related papers

Related papers: Nonseparable Symplectic Neural Networks

200 papers

Hamiltonian systems with multiple timescales arise in molecular dynamics, classical mechanics, and theoretical physics. Long-time numerical integration of such systems requires resolving fast dynamics with very small time steps, which…

Numerical Analysis · Mathematics 2025-10-30 Rui Fang , Richard Tsai

The existence of explicit symplectic integrators for general nonseparable Hamiltonian systems is an open and important problem in both numerical analysis and computing in science and engineering, as explicit integrators are usually more…

Numerical Analysis · Mathematics 2025-04-18 Lijie Mei , Xinyuan Wu , Yaolin Jiang

Symplectic integration algorithms are well-suited for long-term integrations of Hamiltonian systems because they preserve the geometric structure of the Hamiltonian flow. However, this desirable property is generally lost when adaptive…

Astrophysics · Physics 2025-10-20 Miguel Preto , Scott Tremaine

In this paper, we develop a neural network-based approach for time-series prediction in unknown Hamiltonian dynamical systems. Our approach leverages a surrogate model and learns the system dynamics using generalized coordinates (positions)…

Machine Learning · Computer Science 2025-02-03 Taehyeun Kim , Tae-Geun Kim , Anouck Girard , Ilya Kolmanovsky

A recently proposed class of models attempts to learn latent dynamics from high-dimensional observations, like images, using priors informed by Hamiltonian mechanics. While these models have important potential applications in areas like…

Machine Learning · Statistics 2021-11-12 Irina Higgins , Peter Wirnsberger , Andrew Jaegle , Aleksandar Botev

This work presents a hybrid modeling approach to data-driven learning and representation of unknown physical processes and closure parameterizations. These hybrid models are suitable for situations where the mechanistic description of…

Computational Physics · Physics 2021-08-17 Suraj Pawar , Omer San , Adil Rasheed , Ionel M. Navon

Data-driven modeling of physical systems often relies on learning both positions and momenta to accurately capture Hamiltonian dynamics. However, in many practical scenarios, only position measurements are readily available. In this work,…

Computational Physics · Physics 2025-05-06 Ruichen Xu , Zongyu Wu , Luoyao Chen , Georgios Kementzidis , Siyao Wang , Haochun Wang , Yiwei Shi , Yuefan Deng

This work presents two novel approaches for the symplectic model reduction of high-dimensional Hamiltonian systems using data-driven quadratic manifolds. Classical symplectic model reduction approaches employ linear symplectic subspaces for…

Numerical Analysis · Mathematics 2023-08-25 Harsh Sharma , Hongliang Mu , Patrick Buchfink , Rudy Geelen , Silke Glas , Boris Kramer

Data-driven approaches are increasingly popular for identifying dynamical systems due to improved accuracy and availability of sensor data. However, relying solely on data for identification does not guarantee that the identified systems…

Systems and Control · Electrical Eng. & Systems 2024-10-04 Nam T. Nguyen , Juan C. Tique

We present a framework for learning Hamiltonian systems using data. This work is based on a lifting hypothesis, which posits that nonlinear Hamiltonian systems can be written as nonlinear systems with cubic Hamiltonians. By leveraging this,…

Machine Learning · Computer Science 2024-02-09 Süleyman Yildiz , Pawan Goyal , Thomas Bendokat , Peter Benner

A novel hybrid deep neural network architecture is designed to capture the spatial-temporal features of unsteady flows around moving boundaries directly from high-dimensional unsteady flow fields data. The hybrid deep neural network is…

Computational Physics · Physics 2020-06-02 Renkun Han , Zhong Zhang , Yixing Wang , Ziyang Liu , Yang Zhang , Gang Chen

With deep learning gaining attention from the research community for prediction and control of real physical systems, learning important representations is becoming now more than ever mandatory. It is of extreme importance that deep…

Machine Learning · Computer Science 2022-04-13 Saul Santos , Monica Ekal , Rodrigo Ventura

Learning continuous-time stochastic dynamics is a fundamental and essential problem in modeling sporadic time series, whose observations are irregular and sparse in both time and dimension. For a given system whose latent states and…

Machine Learning · Computer Science 2021-04-30 Yingru Liu , Yucheng Xing , Xuewen Yang , Xin Wang , Jing Shi , Di Jin , Zhaoyue Chen

Learning models for dynamical systems in continuous time is significant for understanding complex phenomena and making accurate predictions. This study presents a novel approach utilizing differential neural networks (DNNs) to model…

Machine Learning · Computer Science 2024-12-13 Wenjie Mei , Xiaorui Wang , Yanrong Lu , Ke Yu , Shihua Li

In this paper, we investigate the asymptotic error distributions of symplectic methods for stochastic Hamiltonian systems and further provide Hamiltonian-specific analysis that clarifies the superiority of symplectic methods. Our…

Numerical Analysis · Mathematics 2025-12-04 Chuchu Chen , Xinyu Chen , Jialin Hong , Yuqian Miao

The effectiveness of the Physics Informed Neural Networks (PINNs) for learning the dynamics of constrained Hamiltonian systems is demonstrated using the Dirac theory of constraints for regular systems with holonomic constraints and systems…

Computational Physics · Physics 2025-02-10 Dimitrios A. Kaltsas

Spiking neural networks (SNNs), inspired by the spiking behavior of biological neurons, offer a distinctive approach for capturing the complexities of temporal data. However, their potential for spatial modeling in multivariate time-series…

Machine Learning · Computer Science 2025-08-19 Bang Hu , Changze Lv , Mingjie Li , Yunpeng Liu , Xiaoqing Zheng , Fengzhe Zhang , Wei cao , Fan Zhang

We develop inductive biases for the machine learning of complex physical systems based on the port-Hamiltonian formalism. To satisfy by construction the principles of thermodynamics in the learned physics (conservation of energy,…

Machine Learning · Computer Science 2023-03-28 Quercus Hernández , Alberto Badías , Francisco Chinesta , Elías Cueto

Port-Hamiltonian neural networks (pHNNs) are emerging as a powerful modeling tool that integrates physical laws with deep learning techniques. While most research has focused on modeling the entire dynamics of interconnected systems, the…

Systems and Control · Electrical Eng. & Systems 2024-11-11 G. J. E. van Otterdijk , S. Moradi , S. Weiland , R. Tóth , N. O. Jaensson , M. Schoukens

This paper proposes Hamiltonian Learning, a novel unified framework for learning with neural networks "over time", i.e., from a possibly infinite stream of data, in an online manner, without having access to future information. Existing…

Machine Learning · Computer Science 2024-09-19 Stefano Melacci , Alessandro Betti , Michele Casoni , Tommaso Guidi , Matteo Tiezzi , Marco Gori
‹ Prev 1 3 4 5 6 7 10 Next ›