Non-Asymptotic Confidence Regions for Separable Nonlinear Models

Szentpéteri, Szabolcs and Kovács, Péter and Csáji, Balázs Csanád (2026) Non-Asymptotic Confidence Regions for Separable Nonlinear Models. In: Proceedings of the 65th IEEE Conference on Decision and Control (CDC). IEEE, pp. 1-6. (In Press)

Text E1.pdf - Accepted Version Restricted to Registered users only Download (534kB)

Abstract

This paper studies robust uncertainty quantification for separable nonlinear least squares (SNLLS) problems. We propose two identification methods, (i) Residual-Perturbed Gradient (RPG) and (ii) Global-Fit-Gap (GFG), to construct joint distribution-free confidence regions for both the linear and nonlinear parameters. By exploiting assumed group invariance of the noise (such as symmetry or exchangeability), we apply random perturbations (such as sign-changes or permutations) to build the regions based on resampling and ranking. We prove that both methods guarantee non-asymptotically exact coverage (type I error). Finally, we illustrate the constructions through two numerical experiments: (i) identifying generalized finite impulse response (GFIR) systems using Laguerre polynomials with an adjustable decay rate and (ii) fitting Gaussian radial basis function (RBF) models with variable knots and widths.

Actions (login required)

View Item