Identifying latent state transition in non-linear dynamical systems
It addresses the limitation of previous methods that cannot identify nonlinear transitions, potentially benefiting fields requiring complex dynamical modeling.
This work tackles the problem of identifying latent state transitions in non-linear dynamical systems to improve generalization and interpretability, achieving high accuracy in recovering latent dynamics and predicting future behavior in synthetic settings.
This work aims to improve generalization and interpretability of dynamical systems by recovering the underlying lower-dimensional latent states and their time evolutions. Previous work on disentangled representation learning within the realm of dynamical systems focused on the latent states, possibly with linear transition approximations. As such, they cannot identify nonlinear transition dynamics, and hence fail to reliably predict complex future behavior. Inspired by the advances in nonlinear ICA, we propose a state-space modeling framework in which we can identify not just the latent states but also the unknown transition function that maps the past states to the present. We introduce a practical algorithm based on variational auto-encoders and empirically demonstrate in realistic synthetic settings that we can (i) recover latent state dynamics with high accuracy, (ii) correspondingly achieve high future prediction accuracy, and (iii) adapt fast to new environments.