paper-with-me

Papers

Machine-Learning Non-Conservative Dynamics for New-Physics Detection

2021-05-31 · Ziming Liu, Bohan Wang, Qi Meng, Wei Chen, Max Tegmark, Tie-Yan Liu

Energy conservation is a basic physics principle, the breakdown of which often implies new physics. This paper presents a method for data-driven "new physics" discovery. Specifically, given a trajectory governed by unknown forces, our Neural New-Physics Detector (NNPhD) aims to detect new physics by decomposing the force field into conservative and non-conservative components, which are represented by a Lagrangian Neural Network (LNN) and a universal approximator network (UAN), respectively, trained to minimize the force recovery error plus a constant $\lambda$ times the magnitude of the predicted non-conservative force. We show that a phase transition occurs at $\lambda$=1, universally for arbitrary forces. We demonstrate that NNPhD successfully discovers new physics in toy numerical experiments, rediscovering friction (1493) from a damped double pendulum, Neptune from Uranus' orbit (1846) and gravitational waves (2017) from an inspiraling orbit. We also show how NNPhD coupled with an integrator outperforms previous methods for predicting the future of a damped double pendulum.

📄 PDF Abstract BibTeX arXiv:2106.00026

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine LearningFriction

Similar Papers 제목 키워드 기반

NEXUS: Neural Energy Fields for Physically Consistent Contact-Rich 3D Object Dynamics

2026-06-12 · Qizhen Ying, Guangming Wang, Yangchen Pan, Victor Adrian Prisacariu 외 arxiv

Physics-grounded video generation requires controllable 3D object dynamics that remain physically consistent under contact, deformation, and external forcing. Existing trajectory-based methods often model isolated physic…

Video Generation

Physics-Informed Spiking Neural Networks via Conservative Flux Quantization

2025-11-26 · Chi Zhang, Lin Wang arxiv

Real-time, physically-consistent predictions on low-power edge devices is critical for the next generation embodied AI systems, yet it remains a major challenge. Physics-Informed Neural Networks (PINNs) combine data-driv…

Equilibrium Propagation for Non-Conservative Systems

2026-02-03 · Antonino Emanuele Scurria, Dimitri Vanden Abeele, Bortolo Matteo Mognetti, Serge Massar arxiv

Equilibrium Propagation (EP) is a physics-inspired learning algorithm that uses stationary states of a dynamical system both for inference and learning. In its original formulation it is limited to conservative systems, …

Learning Generalized Hamiltonian Dynamics with Stability from Noisy Trajectory Data

2025-09-08 · Luke McLennan, Yi Wang, Ryan Farell, Minh Nguyen 외 arxiv

We introduce a robust framework for learning various generalized Hamiltonian dynamics from noisy, sparse phase-space data and in an unsupervised manner based on variational Bayesian inference. Although conservative, diss…

Bayesian InferenceGaussian Processes

Exactly conservative physics-informed neural networks and deep operator networks for dynamical systems

2023-11-23 · Elsa Cardoso-Bihlo, Alex Bihlo

We introduce a method for training exactly conservative physics-informed neural networks and physics-informed deep operator networks for dynamical systems. The method employs a projection-based technique that maps a cand…