Lookahead Branching for Neural Network Verification
Its authors withdrew this paper, so there is no full text to read or summarize.
Lists
Only you see this
Abstract
In this paper, we investigate the effect of lookahead branching strategy in neural network verification. We present a general recipe for integrating lookahead into any branch-and-bound search framework, and also describe how in addition to guiding branching, lookahead can generate additional lemmas that accelerate verification. We instantiate the method in two representative branch-and-bound-based verifiers (Marabou and $\alpha$-$\beta$-CROWN), and demonstrate consistent reductions in overall verification time across both systems.
BibTeX
@misc{davis2026lookahead,
author = {Liam Davis and Duo Zhou and Huan Zhang and Guy Katz and Clark Barrett and Haoze Wu},
title = {{Lookahead Branching for Neural Network Verification}},
year = {2026},
eprint = {2607.17290},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2607.17290},
}