Out-of-Domain Generalization in Dynamical Systems Reconstruction

arXiv:2402.18377v1 Announce Type: new
Abstract: In science we are interested in finding the governing equations, the dynamical rules, underlying empirical phenomena. While traditionally scientific models are derived through cycles of human insight and experimentation, recently deep learning (DL) techniques have been advanced to reconstruct dynamical systems (DS) directly from time series data. State-of-the-art dynamical systems reconstruction (DSR) methods show promise in capturing invariant and long-term properties of observed DS, but their ability to generalize to unobserved domains remains an open …

abstract advanced art arxiv cs.lg data deep learning domain experimentation human insight rules science series state systems through time series type