A Geometric Perspective on ML Safety Assurance
Résumé
Some people claim AI-ML suffers from a reliability glass ceiling effect, around 10e-2
per inference, that makes it incompatible with safety-criticality by several orders of magnitude. Others advocate that safety nets and development assurance will overcome this gap so that there is no real concern indeed. We propose an explanation to the reliability plateauing phenomenon based on geometry of approximant adjustment, and on ML verification practices. We advocate the need for a new field we coined as HR ML (Highly Reliable) and UHR ML (Ultra Highly Reliable). Relying on Topological Data Analysis in high dimensions, its aim is to supplement data-science pointbased verification with volume-based verification in order to meet the needed 10e-5 / inf. error rates (and beyond). We argue that process-based ML assurance and safety monitors alone will not overcome the reliability barrier. Our HR-ML concept for safety-related applications is a research proposition at the confluence of ML assurance and system assurance.
Fichier principal
DSN23_P8677_Geometric_perspective_ML_assurance.pdf (915.75 Ko)
Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)