Work

Pick-To-Learn for Systems and Control: theoretical review with a showcase in reachability analysis

Year: 2025

Type: conference-paper

Abstract: Data-Driven methods have become popular tools for tackling increasingly complex design problems in systems and control. In safety critical settings, deploying these methods requires rigorous safety and performance guarantees. Unfortunately, existing approaches often achieve this requirement at the cost of sacrificing valuable data for testing and calibration, or by restricting the design space, thus leading to suboptimal performances. In this work, we introduce Pick-To-Learn (P2L) for Systems and Control, a framework that builds on recent results in sample compression theory to equip any data-driven control method with safety and performance guarantees. Crucially, P2L enables the use of all available data to jointly synthesize and certify the design, eliminating the need to set aside data for calibration or validation purposes. As a result, P2L delivers designs and certificates that improve the current state of the art. We demonstrate this on existing benchmarks in reachability analysis.

Source: Proceedings of the IEEE Conference on Decision & Control, including the Symposium on Adaptive Processes

DOI: 10.1109/cdc57313.2025.11312219

Authors: Dario Paccagnan, Daniel Marks, Marco C. Campi, Simone Garatti

Institutions: Imperial College London, University of Brescia, Politecnico di Milano

Language: English

Topic: Formal Methods in Verification

Subfield: Computational Theory and Mathematics

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: UK Research and Innovation, Engineering and Physical Sciences Research Council

Award: COmpetition models and cross-Subsidies for equitable and green MObility - COSMO