Automated Discovery of Operable Dynamics from Videos

Kuang Huang; Dong Heon Cho; Boyuan Chen

eess.SYOct 14, 2024

Automated Discovery of Operable Dynamics from Videos

Authors: Kuang Huang, Dong Heon Cho, Boyuan Chen

Organizations: Department of Applied Physics and Applied Mathematics, Columbia University, 500 W. 120th Street, New York, 10027, NY, USA. · Department of Computer Science, Duke University, 308 Research Dr., Durham, 27705, NC, USA. · Department of Mechanical Engineering and Material Science, Duke University, 121 Hudson Hall, Durham, 27708, NC, USA. · Department of Electrical and Computer Engineering, Duke University, 100 Science Dr., Durham, 27708, NC, USA.

Abstract

Dynamical systems form the foundation of scientific discovery, traditionally modeled with predefined state variables such as the angle and angular velocity, and differential equations such as the equation of motion for a single pendulum. We introduce a framework that automatically discovers a low-dimensional and operable representation of system dynamics, including a set of compact state variables that preserve the smoothness of the system dynamics and a differentiable vector field, directly from video without requiring prior domain-specific knowledge. The prominence and effectiveness of the proposed approach are demonstrated through both quantitative and qualitative analyses of a range of dynamical systems, including the identification of stable equilibria, the prediction of natural frequencies, and the detection of chaotic and limit cycle behaviors. The results highlight the potential of our data-driven approach to advance automated scientific discovery.

Explore similar work

Information bottleneck for learning the phase space of dynamics from high-dimensional experimental data
Apr 27, 2026K. Michael Martini, Eslam Abdelaleem, Paarth Gulati +1Phase Space High-Dimensional Data
Geometric Dictionary Learning of Dynamical Systems with Optimal Transport
May 18, 2026Thibaut Germain, Sami Chemlal, Rémi Flamary +2Dynamical Systems Learning Dynamics
Extracting Governing Equations from Latent Dynamics via Multi-View Contrastive Learning
Jun 11, 2026Paolo Muratore, Mackenzie Weygandt MathisLatent Dynamics Noisy Data

Apr 27, 2026 · physics.data-anJ/K move · Enter open · S save

Information bottleneck for learning the phase space of dynamics from high-dimensional experimental data

K. Michael Martini, Eslam Abdelaleem, Paarth Gulati, Ilya Nemenman

Department of Physics, Emory University, Atlanta, GA, USA · Schools of Physics and Psychology, Georgia Institute of Technology, Atlanta, GA, USA · Initiative in Theory and Modeling of Living Systems, Emory University, Atlanta, GA, USA · Department of Biology, Emory University, Atlanta, GA, USA

Identifying the dynamical state variables of a system from high-dimensional observations is a central problem across physical sciences. The challenge is that the state variables are not directly observable and must be inferred from raw high-dimensional data without supervision. Here we introduce DySIB (Dynamical Symmetric Information Bottleneck) as a method to learn low-dimensional representations of time-series data by maximizing predictive mutual information between past and future observation windows while penalizing representation complexity. This objective operates entirely in latent space and avoids reconstruction of the observations. We apply DySIB to an experimental video dataset of a physical pendulum, where the underlying state space is known. The method, with hyperparameters of the learning architecture set self-consistently by the data, recovers a two-dimensional representation that matches the dimensionality, topology, and geometry of the pendulum phase space, with the learned coordinates aligning smoothly with the canonical angle and angular velocity. These results demonstrate, on a well-characterized experimental system, that predictive information in latent space can be used to recover interpretable dynamical coordinates directly from high-dimensional data.

Phase Space High-Dimensional Data Information Bottleneck

Open paper Ask about it PDF

Abstract

Explore similar work

Information bottleneck for learning the phase space of dynamics from high-dimensional experimental data

Geometric Dictionary Learning of Dynamical Systems with Optimal Transport

Extracting Governing Equations from Latent Dynamics via Multi-View Contrastive Learning