Learning to Split: A Reinforcement-Learning-Guided Splitting Heuristic for Neural Network Verification

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Swisa, Maya, Katz, Guy
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912758231990272
author Swisa, Maya
Katz, Guy
author_facet Swisa, Maya
Katz, Guy
contents State-of-the-art neural network verifiers operate by encoding neural network verification as constraint satisfaction problems. When dealing with standard piecewise-linear activation functions, such as ReLUs, verifiers typically employ branching heuristics that break a complex constraint satisfaction problem into multiple, simpler problems. The verifier's performance depends heavily on the order in which this branching is performed: a poor selection may give rise to exponentially many sub-problem, hampering scalability. Here, we focus on the setting where multiple verification queries must be solved for the same neural network. The core idea is to use past experience to make good branching decisions, expediting verification. We present a reinforcement-learning-based branching heuristic that achieves this, by applying a learning from demonstrations (DQfD) techniques. Our experimental evaluation demonstrates a substantial reduction in average verification time and in the average number of iterations required, compared to modern splitting heuristics. These results highlight the great potential of reinforcement learning in the context of neural network verification.
format Preprint
id arxiv_https___arxiv_org_abs_2512_10747
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning to Split: A Reinforcement-Learning-Guided Splitting Heuristic for Neural Network Verification
Swisa, Maya
Katz, Guy
Logic in Computer Science
State-of-the-art neural network verifiers operate by encoding neural network verification as constraint satisfaction problems. When dealing with standard piecewise-linear activation functions, such as ReLUs, verifiers typically employ branching heuristics that break a complex constraint satisfaction problem into multiple, simpler problems. The verifier's performance depends heavily on the order in which this branching is performed: a poor selection may give rise to exponentially many sub-problem, hampering scalability. Here, we focus on the setting where multiple verification queries must be solved for the same neural network. The core idea is to use past experience to make good branching decisions, expediting verification. We present a reinforcement-learning-based branching heuristic that achieves this, by applying a learning from demonstrations (DQfD) techniques. Our experimental evaluation demonstrates a substantial reduction in average verification time and in the average number of iterations required, compared to modern splitting heuristics. These results highlight the great potential of reinforcement learning in the context of neural network verification.
title Learning to Split: A Reinforcement-Learning-Guided Splitting Heuristic for Neural Network Verification
topic Logic in Computer Science
url https://arxiv.org/abs/2512.10747