3 papers
math.NA2026
1-Lipschitz Neural Networks on Hadamard Manifolds
Davide Murari, Marta Ghirardelli, Ben Adcock +3
Controlling the Lipschitz constant of a neural network is a standard way to promote robustness and stability. Most existing constraining strategies are designed for Euclidean space…
cs.LG2026
Learning Forced Multibody Dynamics on Lie Groups
Martine Dyring Hansen, Marta Ghirardelli, Elena Celledoni +2
We propose an architecture for learning the dynamics of mechanical systems based on discrete forced Euler-Lagrange equations on Lie groups using only position data. By formulating…
eess.SY2025
Learning mechanical systems from real-world data using discrete forced Lagrangian dynamics
Martine Dyring Hansen, Elena Celledoni, Benjamin Kwanen Tapley
We introduce a data-driven method for learning the equations of motion of mechanical systems directly from position measurements, without requiring access to velocity data. This is…