Skip to yearly menu bar Skip to main content


Generalizing to New Physical Systems via Context-Informed Dynamics Model

Matthieu Kirchmeyer · Yuan Yin · Jérémie DONA · Nicolas Baskiotis · alain rakotomamonjy · Patrick Gallinari

Hall E #313

Keywords: [ MISC: Transfer, Multitask and Meta-learning ] [ APP: Physics ] [ DL: Algorithms ]


Data-driven approaches to modeling physical systems fail to generalize to unseen systems that share the same general dynamics with the learning domain, but correspond to different physical contexts. We propose a new framework for this key problem, context-informed dynamics adaptation (CoDA), which takes into account the distributional shift across systems for fast and efficient adaptation to new dynamics. CoDA leverages multiple environments, each associated to a different dynamic, and learns to condition the dynamics model on contextual parameters, specific to each environment. The conditioning is performed via a hypernetwork, learned jointly with a context vector from observed data. The proposed formulation constrains the search hypothesis space for fast adaptation and better generalization across environments with few samples. We theoretically motivate our approach and show state-of-the-art generalization results on a set of nonlinear dynamics, representative of a variety of application domains. We also show, on these systems, that new system parameters can be inferred from context vectors with minimal supervision.

Chat is not available.