cs.LGJul 19, 2026

Lookahead Branching for Neural Network Verification

Authors: Liam Davis, Duo Zhou, Huan Zhang, Guy Katz, Clark Barrett, Haoze Wu

Organizations: Amherst College · University of Illinois Urbana-Champaign · Hebrew University of Jerusalem · Stanford University

Abstract

In this work, we investigate the effect of lookahead branching strategies in neural network verification. We present a general recipe to integrate lookahead into any branch-and-bound verifier and demonstrate how one of the current state-of-the-art branching heuristics, FSB, can be viewed as a special instantiation of the lookahead branching strategy. We also describe how, in addition to improving the quality of branching decisions, lookahead can generate additional lemmas that accelerate verification. We instantiate the method in two representative branch-and-bound-based verifiers (Marabou and αα-ββ-CROWN), and demonstrate that lookahead leads to consistent speedups in verification time and up to 57%57\% more solved instances. Code is available at https://github.com/ai-ar-research/lookahead-branching.

Explore similar work

CardsList