Finite sample learning of moving targets

Journal article

We consider a moving target that we seek to learn from samples. Our results extend randomized techniques developed in control and optimization for a constant target to the case where the target is changing. We derive a novel bound on the number of samples that are required to construct a probably approximately correct (PAC) estimate of the target. Furthermore, when the moving target is a convex polytope, we provide a constructive method of generating the PAC estimate using a mixed integer linear program (MILP). The proposed method is demonstrated on an application to autonomous emergency braking.

Authors: Vertovec, N; Margellos, K; Prandini, M

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Elsevier
• Journal: Automatica
• Volume: 185
• Article number: 112763
• Publication date: 2025-12-18
• Acceptance date: 2025-11-10
• DOI: 10.1016/j.automatica.2025.112763
• EISSN: 1873-2836
• ISSN: 0005-1098
• Language: English
• Keywords: statistical learning theory; randomized methods; probably approximately correct learning; data-driven algorithms; drifting target concept