SOURCE-LINKED INTELLIGENCE

Generalization as a robust performance property of learning-enabled dynamical systems

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

By focusing on algorithmic stability as a means of establishing out-of-sample bounds, we provide a system-theoretic interpretation of generalization in learning-enabled dynamical systems arising in data-driven optimization and feedback control approximation. Given two neighboring datasets, we specifically model sample replacement as an exogenous disturbance acting on a sensitivity system, while the incremental behavior of the data-dependent operator is encoded through an integral quadratic constraint. By relying on dissipativity arguments, we establish a matrix inequality-based certificate and

Read original source ↗ Open in workspace

recordType

paper

region

Global