Sequential operator learning under dependent data

arXiv:2608.24426v1 Announce Type: cross Abstract: Learning operators from sequentially collected data arises in adaptive experimental design, Bayesian optimization, and dynamical-system modelling, where observations may be dependent, and future inputs or sensing operators may depend on preceding data. We derive time-uniform self-normalized concentration bounds for stochastic processes in Hilbert spaces with vector-valued noise. We use these bounds to obtain regression-error guarantees for linear operators, including targets outside the Hilbert estimation space, and for nonlinear parametric operators trained with strongly convex losses and regularizers. Our results allow possibly infinite-dimensional inputs and outputs without independence or mixing assumptions, providing a major step towards convergence guarantees for adaptive operator learning and learning from stochastic dynamical data.

BALLAST: Bayesian Active Learning with Look-ahead Amendment for Sea-drifter Trajectories under Spatio-Temporal Vector Fields
Symmetric Hermite quadrature-based balanced truncation for learning linear dynamical systems from derivative data
Adaptive deep nonparametric regression from dependent data under covariate shift
Self-Modulating Quantum Fast-Weight Programmers for Efficient Adaptive Sequential Learning

Source: arXiv cs.LG | 2026-08-26

Related