[2603.25273] Distribution and Clusters Approximations as Abstract Domains in Probabilistic Abstract Interpretation to Neural Network Analysis

Computer Science > Artificial Intelligence arXiv:2603.25273 (cs) [Submitted on 26 Mar 2026] Title:Distribution and Clusters Approximations as Abstract Domains in Probabilistic Abstract Interpretation to Neural Network Analysis Authors:Zhuofan Zhang, Herbert Wiklicky View a PDF of the paper titled Distribution and Clusters Approximations as Abstract Domains in Probabilistic Abstract Interpretation to Neural Network Analysis, by Zhuofan Zhang and Herbert Wiklicky View PDF Abstract:The probabilistic abstract interpretation framework of neural network analysis analyzes a neural network by analyzing its density distribution flow of all possible inputs. The grids approximation is one of abstract domains the framework uses which abstracts concrete space into grids. In this paper, we introduce two novel approximation methods: distribution approximation and clusters approximation. We show how these two methods work in theory with corresponding abstract transformers with help of illustrations of some simple examples. Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2603.25273 [cs.AI]   (or arXiv:2603.25273v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2603.25273 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Zhuofan Zhang [view email] [v1] Thu, 26 Mar 2026 10:09:58 UTC (78 KB) Full-text links: Access Paper: View a PDF of the paper titled Distribution and Clusters Approximations as Abstract Domains in Probabili...