Hybrid Dynamical Systems

Follow this topic Ask about this topic

Latest papers

15 papers1 paper in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Unrolled gradients in disguise: bridging interpolation-based and Jacobian regularization for stable neural dynamics
Nov 2, 2026Maya Janvier, Etienne MeunierNeural Network Stability Neural ODEs
LOCEAN, Sorbonne University, Paris, France · Inria, Paris, France
Hybrid-time PINNs: Discontinuity-Aware Physics-Informed Neural Networks for Learning Hybrid Dynamical Systems
Oct 24, 2026Shivanshu Tripathi, Maziar RaissiHybrid Dynamical Systems Physics-Informed ML
Department of Electrical and Computer Engineering, University of California, Riverside, Riverside, CA 92521, USA. · Department of Mathematics, University of California, Riverside, Riverside, CA 92521, USA.
The Effect of Gait Stability Based on Two Types of Impact Strategies for Two-Link Walking and Brachiating Robots
Oct 1, 2026Alan Estrada Flores, Nelson RosaHybrid Dynamical Systems Dynamical Systems
Illinois Institute of Technology, Chicago IL 60616, USA
Learning Continuous Neural Representation of Stochastic Hybrid Systems
Sep 30, 2026Sangli Teng, Hang Liu, Koushil SreenathDynamical Systems Stochastic Differential Equations
Conservative Hybrid Graph Networks for Process Systems with Learned Routing
Aug 28, 2026Paolo GuidaHybrid Dynamical Systems Physics-Informed GNNs
Physical Science and Engineering King Abdullah University of Science and Technology (KAUST) Thuwal, Saudi Arabia
A Differentiable Composite Approximation Framework for Autonomous Underwater Vehicle Maneuvering Modeling from Sea-Trial Data
Jun 18, 2026Aobo Wang, Aifei Xia, Zihao Wang +1Hybrid Dynamical Systems Dynamical Systems
College of Shipbuilding Engineering, Harbin Engineering University, Harbin, 150001, China · China Academy of Aerospace Aerodynamics, Beijing, 100074, China · Institute of Artificial Intelligence, Shanghai University, Shanghai, 200444, China +1
OrthoReg: Orthogonal Regularization for Hybrid Symbolic-Neural Dynamical Systems
Jun 17, 2026Till Richter, Niki KilbertusSparse Identification of Nonlinear Dynamics Neural Network Interpretability
Technical University of Munich · Helmholtz Munich
Embedding Hybrid Systems into Continuous Latent Vector Fields
Jun 9, 2026Sangli Teng, Hang Liu, Koushil SreenathLatent Dynamics Modeling System Identification
University of California, Berkeley, CA, USA · University of Michigan, Ann Arbor, MI, USA
Differentiable Parameter Optimization for DAEs with State-Dependent Events
May 6, 2026Ion Matei, Maksym Zhenirovskyy, Anthony WongHybrid Dynamical Systems Dynamical Systems
Fujitsu Research of America
Learning Control Policies to Provably Satisfy Hard Affine Constraints for Black-Box Hybrid Dynamical Systems
Apr 24, 2026Aayushi Shrivastava, Kartik Nagpal, Sairam Jinkala +2Hybrid Dynamical Systems Dynamical Systems
Department of Mechanical Engineering, University of California Berkeley, Berkeley, CA 94709, USA
Model Predictive Control of Hybrid Dynamical Systems
Apr 23, 2026Ricardo G. Sanfelice, Berk AltinHybrid Dynamical Systems Dynamical Systems
Department of Electrical and Computer Engineering, University of California, Santa Cruz, CA, 94107 USA
HALO: Hybrid Auto-encoded Locomotion with Learned Latent Dynamics, Poincaré Maps, and Regions of Attraction
Apr 20, 2026Blake Werner, Sergio A. Esteban, Massimiliano De Sa +2Dynamical Systems Humanoid Robot Locomotion
Caltech, Pasadena, CA, USA · NC State University, Raleigh, NC, USA
Differentiable Invariant Sets for Hybrid Limit Cycles with Application to Legged Robots
Apr 6, 2026Varun Madabushi, Akash Harapanahalli, Samuel Coogan +1Hybrid Dynamical Systems Dynamical Systems
School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, 30332, USA.
Finite-Step Invariant Sets for Hybrid Systems with Probabilistic Guarantees
Apr 6, 2026Varun Madabushi, Elizabeth Dietrich, Hanna Krasowski +1Hybrid Dynamical Systems Dynamical Systems
Georgia Institute of Technology · University of California, Berkeley
Path Integral Particle Filtering for Hybrid Systems via Saltation Matrices
Mar 1, 2026Karthik Shaji, Sreeranj Jayadevan, Bo Yuan +2Particle Filtering Robot State Estimation
Graduate Student, Daniel Guggenheim School of Aerospace Engineering · MathWorks · PlusAI +1

Nov 2, 2026J/K move · Enter open · S save

Unrolled gradients in disguise: bridging interpolation-based and Jacobian regularization for stable neural dynamics

Maya Janvier, Etienne Meunier

LOCEAN, Sorbonne University, Paris, France · Inria, Paris, France

Neural Network Stability Neural ODEs Jacobian Regularization Hybrid Dynamical Systems

Open paper AskPDF arXiv

Hybrid models and neural differential equations (NDEs) are becoming increasingly important for modelling physical systems; however, they often encounter stability and accuracy issues during long-term integration. Training on unrolled trajectories is known to limit these divergences but quickly becomes too computationally expensive due to the need to compute gradients over an iterative process, making this method impractical for large-scale physical systems (e.g. weather and climate forecasting). Two popular paradigms for improving the stability of learned dynamics are to train on interpolated or noisy samples or to regularize the Jacobian of the learned representation. In this work, we demonstrate that these paradigms can be understood under a common lens and that they both correspond to an approximation of the gradients obtained in an unrolled learning strategy. Building on this understanding, we derive a principled and complete approach to regularize training and demonstrate its impact on the stability of learned dynamical systems.