Spectral Flow Learning Theory: Finite-Sample Guarantees for Vector-Field Identification
This work addresses a fundamental challenge in dynamical systems for researchers and practitioners, offering theoretical guarantees for vector-field identification, though it appears incremental as it builds on existing methods like variable-step linear multistep methods.
The paper tackles the problem of identifying continuous-time vector fields from irregularly sampled trajectories by introducing spectral flow learning, providing finite-sample, high-probability guarantees with explicit discretization bias and statistical rates, as demonstrated in simulations on a mass-spring system.
We study the identification of continuous-time vector fields from irregularly sampled trajectories. We introduce spectral flow learning, which learns in a windowed flow space using a lag-linear label operator that aggregates lagged Koopman actions. We provide finite-sample, high-probability (FS-HP) guarantees for the class of variable-step linear multistep methods (vLMM). The FS-HP rates are constructed using spectral regularization with qualification-controlled filters for flow predictors under standard source and filter assumptions. A multistep observability inequality links flow error to vector-field error and yields two-term bounds that combine a statistical rate with an explicit discretization bias from vLMM theory. Simulations on a controlled mass-spring system corroborate the theory and clarify conditioning, step-sample tradeoffs, and practical implications.