Year: 2026
Type: preprint
Abstract: State-of-the-art neural network verifiers use the branch-and-bound procedure as their core solving mechanism. We introduce an inprocessing framework for neural network verification driven by the lookahead procedure. Under this framework, lookahead derives new lemmas over the phases of unstable ReLUs, which are collected into an implication graph that is used to prune the search space and vivify boolean cuts. We instantiate the framework in two state-of-the-art verifiers, Marabou and $α$-$β$-CROWN, and demonstrate that it improves performance in both, proving up to 34% more instances unsatisfiable.
Source: arXiv (Cornell University)
Authors: Davis, Liam, Wu, Haoze
Institution: Amherst College
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7172292013
Cites:
Cited by:
Related to: