Model Releases
Non-Asymptotic Bounds for Closed-Loop Identification of Sub-Exponentially Growing Nonlinear Stochastic Systems
arXiv:2412.04157v2 Announce Type: replace-cross Abstract: We investigate the problem of least squares parameter estimation from single-trajectory data for discrete-time, unstable, closed-loop nonlinea
arXiv:2412.04157v2 Announce Type: replace-cross Abstract: We investigate the problem of least squares parameter estimation from single-trajectory data for discrete-time, unstable, closed-loop nonlinear stochastic systems. Specifically, we consider nonlinear systems with linearly parametrised uncertainty and additive i.i.d. process noise, in feedback with a control policy that is intentionally perturbed by an exploratory input. Assuming the open-loop dynamics satisfy a particular sub-exponential input-to-state growth property, and a region of the state space produces informative data, we establish non-asymptotic guarantees on the estimation error at times when the state trajectory evolves in this region. If the whole state space is informative, high-probability guarantees on the error hold for all times. Examples are provided where our results are useful for analysis beyond existing works.
Related
- Error Bounds for a Diffusion Model-Based Drift Estimator
- Learning piecewise-smooth dynamical systems
- CLT-Optimal Parameter Error Bounds for Linear System Identification
Source: arXiv cs.LG | 2026-08-27