Tag
We introduce SALTO, a Koopman-based lifted transfer operator framework that anchors learned dynamics to a simulator's linearized propagator, enabling accurate finite-amplitude source inference and adjoint-like sensitivities at a fraction of the cost of repeated nonlinear solver runs across three nonlinear PDE systems.
This paper presents methods for differentiable parameter optimization of differential-algebraic equations (DAEs) with state-dependent events, comparing automatic differentiation through simulation with explicit discrete-adjoint methods.