Certification of Machine Learning Models via Directional Sharpness

Computer Science > Machine Learning [Submitted on 23 Jun 2026] Certification of Machine Learning Models via Directional Sharpness Gefei Tan, Adria Gascon, Sarah Meiklejohn, Mariana Raykova In machine learning, model certification has been identified as an important method for gaining assurance about a model's trustworthiness and quality. A model's quality is largely determined by its ability to generalize, i.e., to perform well on data beyond what it was trained on. It is not possible to certify generalization directly, however, as it depends on unknown data and is not directly measurable. Proxies such as test accuracy can be misleading when the training process is perturbed (intentionally or accidentally), and metrics such as sharpness -- which has an empirically supported link to generalization -- are computationally expensive and can also serve as unreliable signals when training deviates from a prescribed procedure. In this work, we propose directional sharpness, a metric designed to efficiently and reliably indicate generalization despite potential training deviations. We provide empirical and analytical evidence that directional sharpness (1) correlates more strongly with generalization than existing metrics and (2) identifies models with poor generalization more reliably than existing metrics. Furthermore, directional sharpness is efficiently computable in model auditing settings, where the verifier has access to training data, and via zero-knowledge proofs that certify quality without revealing training data. Subjects: Machine Learning (cs.LG); Cryptography and Security (cs.CR) Cite as: arXiv:2606.25004 [cs.LG]   (or arXiv:2606.25004v1 [cs.LG] for this version)   https://doi.org/10.48550/arXiv.2606.25004 Focus to learn more Submission history From: Gefei Tan [view email] [v1] Tue, 23 Jun 2026 17:07:25 UTC (78 KB) Access Paper: HTML (experimental) view license Current browse context: cs.LG < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.CR References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)