[00939] Learning Dynamical Systems from Invariant Measures
Session Time & Room : 5D (Aug.25, 15:30-17:10) @G709
Type : Contributed Talk
Abstract : Standard data-driven techniques for learning dynamical systems struggle when observational data has been sampled slowly and state derivatives cannot be accurately estimated. To address this challenge, we assume that the available measurements reliably describe the asymptotic statistics of the dynamical process in question, and we instead treat invariant measures as inference data. We reformulate the velocity learning as a PDE constrained optimization and present several numerical examples to demonstrate the effectiveness of the proposed approach.