זיהוי והגשמה: למידת השוואתית של דינמיקות פורט-המילטוניאן סתומות מבוזרות

תקציר מקורי באנגליתarXiv:2605.16682v2 Announce Type: replace Abstract: Identifying latent state representations and dynamics is essential when direct modeling in observation space is infeasible, particularly under partial and high-dimensional observations. In such settings, representation learning and physics-aware modeling are inherently coupled. We propose CIPHER, a two-stage identify-then-realize framework for learning latent port-Hamiltonian models of conservative and dissipative systems. First, a contrastive teacher jointly learns an encoder and a neural ODE to obtain predictive state representations from observation histories. Second, a student learns an invertible nonlinear coordinate transformation and port-Hamiltonian dynamics by matching encoded observed futures. We establish sufficient conditions