Extracting Governing Equations from Latent Dynamics via Multi-View Contrastive Learning
This work addresses the challenge of identifying latent dynamical systems from noisy measurements, which is crucial for scientific discovery and neural data analysis.
DYSCO uses multi-view temporal contrastive learning to recover latent trajectories and governing equations from noisy, high-dimensional observations, achieving accurate recovery across chaotic, oscillatory, and metastable dynamics under Gaussian and Poisson noise.
Identifying latent dynamical systems from noisy, high-dimensional measurements is a central problem at the intersection of representation learning, system identification, and scientific discovery. We present DYSCO, a multi-view temporal contrastive learning algorithm that jointly recovers latent trajectories and the governing dynamics from such observations, by leveraging multiple independent noisy views of the same underlying process to disentangle signal from noise. By parameterizing the dynamics in a structured functional basis, our framework further enables symbolic recovery of the governing equations within an affine gauge. We offer theoretical guarantees for strong identification up to an affine indeterminacy, extending prior identifiability results to the realistic setting of noisy nonlinear observations. Empirically, we demonstrate accurate recovery of both latent trajectories and flow fields across a diverse set of dynamical regimes (e.g., chaotic, oscillatory, and metastable) under both Gaussian and Poisson observation noise, the latter being particularly relevant for neural recordings.