English
Related papers

Related papers: Pioneer: Physics-informed Riemannian Graph ODE for…

200 papers

We propose a geometrical approach to the investigation of Hamiltonian systems on (Pseudo) Riemannian manifolds. A new geometrical criterion of instability and chaos is proposed. This approach is more generic than well known reduction to the…

Astrophysics · Physics 2007-05-23 A. A. Kocharyan

This work is devoted to studying dynamic interpolation for obstacle avoidance. This is a problem that consists of minimizing a suitable energy functional among a set of admissible curves subject to some interpolation conditions. The given…

Optimization and Control · Mathematics 2018-09-11 Anthony Bloch , Margarida Camarinha , Leonardo Colombo

The order/dimension of models derived on the basis of data is commonly restricted by the number of observations, or in the context of monitored systems, sensing nodes. This is particularly true for structural systems (e.g., civil or…

Machine Learning · Computer Science 2022-12-01 Zhilu Lai , Wei Liu , Xudong Jian , Kiran Bacsa , Limin Sun , Eleni Chatzi

Oscillator Ising machines (OIMs) represent an exemplar case of using physics-inspired non-linear dynamical systems to solve computationally challenging combinatorial optimization problems (COPs). The computational performance of such…

Machine Learning · Computer Science 2025-04-15 E. M. H. E. B. Ekanayake , N. Shukla

The data-driven discovery of interpretable models approximating the underlying dynamics of a physical system has gained attraction in the past decade. Current approaches employ pre-specified functional forms or basis functions and often…

Machine Learning · Computer Science 2025-07-30 Rahul Golder , M. M. Faruque Hasan

Neural networks with physics based inductive biases such as Lagrangian neural networks (LNN), and Hamiltonian neural networks (HNN) learn the dynamics of physical systems by encoding strong inductive biases. Alternatively, Neural ODEs with…

Machine Learning · Computer Science 2024-06-18 Suresh Bishnoi , Ravinder Bhattoo , Sayan Ranu , N. M. Anoop Krishnan

We study the Riemannian geometry of the Deep Linear Network (DLN) as a foundation for a thermodynamic description of the learning process. The main tools are the use of group actions to analyze overparametrization and the use of Riemannian…

Machine Learning · Computer Science 2026-05-22 Govind Menon , Tianmin Yu

Steering a language model - intervening on its internal activations to change downstream behaviour - has recently expanded beyond linear interpolation to nonlinear methods such as angular and kernelized steering, which define intervention…

Incorporating the Hamiltonian structure of physical dynamics into deep learning models provides a powerful way to improve the interpretability and prediction accuracy. While previous works are mostly limited to the Euclidean spaces, their…

Machine Learning · Computer Science 2022-10-04 Oswin So , Gongjie Li , Evangelos A. Theodorou , Molei Tao

An increasingly common viewpoint is that protein dynamics data sets reside in a non-linear subspace of low conformational energy. Ideal data analysis tools for such data sets should therefore account for such non-linear geometry. The…

Biomolecules · Quantitative Biology 2023-10-27 Willem Diepeveen , Carlos Esteve-Yagüe , Jan Lellmann , Ozan Öktem , Carola-Bibiane Schönlieb

The inductive biases of graph representation learning algorithms are often encoded in the background geometry of their embedding space. In this paper, we show that general directed graphs can be effectively represented by an embedding model…

Machine Learning · Statistics 2021-06-17 Aaron Sim , Maciej Wiatrak , Angus Brayne , Páidí Creed , Saee Paliwal

Generating physically feasible dynamics in a data-driven context is challenging, especially when adhering to physical priors expressed in specific equations or formulas. Existing methodologies often overlook the integration of physical…

Machine Learning · Computer Science 2026-02-16 Zihan Zhou , Xiaoxue Wang , Tianshu Yu

Neural ordinary differential equations (NODE) have garnered significant attention for their design of continuous-depth neural networks and the ability to learn data/feature dynamics. However, for high-dimensional systems, estimating…

Machine Learning · Computer Science 2025-10-07 Muhao Guo , Haoran Li , Yang Weng

In this paper, we propose RiemannianFlow, a deep generative model that allows robots to learn complex and stable skills evolving on Riemannian manifolds. Examples of Riemannian data in robotics include stiffness (symmetric and positive…

Robotics · Computer Science 2023-09-27 Weitao Wang , Matteo Saveriano , Fares J. Abu-Dakka

Newtonian, Lagrangian, and Hamiltonian dynamical systems are well formalized mathematically. They give rise to geometric structures describing motion of a point in smooth manifolds. Riemannian metric is a different geometric structure…

Differential Geometry · Mathematics 2007-05-23 Ruslan Sharipov

Computational optimal transport (OT) offers a principled framework for generative modeling. Neural OT methods, which use neural networks to learn an OT map (or potential) from data in an amortized way, can be evaluated out of sample after…

Machine Learning · Computer Science 2026-02-04 Alessandro Micheli , Yueqi Cao , Anthea Monod , Samir Bhatt

We show that the standard discrete update rule of transformer layers can be naturally interpreted as a forward Euler discretization of a continuous dynamical system. Our Transformer Flow Approximation Theorem demonstrates that, under…

Machine Learning · Computer Science 2025-05-26 Jacob Fein-Ashley

Decentralized optimization on Riemannian manifolds is foundational for many modern machine learning and signal processing applications in which data are non-Euclidean and generated and processed in a distributed manner. Although intrinsic…

Optimization and Control · Mathematics 2026-03-19 Duc Toan Nguyen , César A. Uribe

In part III is realized the consistent development of Heisenberg--Dyson's two-layer matrix approximation to the graph formalism for postulating discrete physical objects (DPO) introduced in parts I-II in the form of discrete sets of…

General Physics · Physics 2007-05-23 V. E. Asribekov

Grasping objects of different shapes and sizes - a foundational, effortless skill for humans - remains a challenging task in robotics. Although model-based approaches can predict stable grasp configurations for known object models, they…

Robotics · Computer Science 2022-11-22 Malte Mosbach , Sven Behnke