Metraipolis › archive › dc_cdb2855f53fc
Verifying Neural Networks with Reinforcement Learning — arXiv:2609.34553
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34553
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T22:38:23.126Z
- SHA-256 of the archived text
a561282cdfdec8cb013869dc8d79e1dc6b5a5165cff197e0473426213e04c039- Stable URL of this page
https://metraipolis.com/documento/dc_cdb2855f53fc
How to cite
Verifying Neural Networks with Reinforcement Learning — arXiv:2609.34553 — arXiv (en), https://arxiv.org/abs/2609.34553 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cdb2855f53fc (Metraipolis archive dc_cdb2855f53fc, sha256 a561282cdfdec8cb013869dc8d79e1dc6b5a5165cff197e0473426213e04c039)
BibTeX
@misc{dccdb2855f53fc,
title = {Verifying Neural Networks with Reinforcement Learning — arXiv:2609.34553},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34553},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cdb2855f53fc; sha256 a561282cdfdec8cb013869dc8d79e1dc6b5a5165cff197e0473426213e04c039},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34553. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Formal verification can play a key role in ensuring the reliability of Deep Neural Networks (DNNs) deployed in safety-critical systems. Modern DNN verifiers employ a branch-and-bound framework, which alternates between branching (splitting into smaller subproblems) and bounding (pruning subproblems) to efficiently explore the verification space. However, existing branching heuristics make greedy decisions based on static scoring functions. They do not anticipate long-term efficiency or leverage the growing availability of verification data to improve performance. This work introduces RSB, a reinforcement learning framework that learns to refine baseline branching heuristics. It trains an actor-critic architecture to maximize cumulative future rewards rather than immediate scores. The actor generates attention weights from observations of raw neuron features and learned graph embeddings, which rescale baseline heuristic scores to guide neuron branching. Evaluation on 600 challenging instances demonstrates that RSB consistently outperforms state-of-the-art branching heuristics, solving 11% more instances while reducing branch exploration by 50%. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2609.34553 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T22:14:28.222Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).