arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1802.03685cs.AIcs.LGcs.LO
收藏

从单位监督学习SAT求解器

Learning a SAT Solver from Single-Bit Supervision

Stanford University(斯坦福大学);Microsoft Research(微软研究院)

Daniel Selsam, Matthew Lamm, Benedikt Bünz, Percy Liang, Leonardo de Moura, David L. Dill

摘要:

我们提出了NeuroSAT,一个消息传递神经网络,学习解决SAT问题后,只被训练为一个分类器,以预测可满足性。虽然它与最先进的SAT求解器没有竞争力,但NeuroSAT可以通过简单地运行更多的迭代来解决比训练过程中看到的更大、更困难的问题。此外,NeuroSAT还可以推广到新的分布;在仅对随机SAT问题进行训练后,在测试时,它可以解决SAT问题编码图着色,团检测,支配集和顶点覆盖问题,所有这些都是在小随机图上的分布范围内。

英文摘要:

We present NeuroSAT, a message passing neural network that learns to solve SAT problems after only being trained as a classifier to predict satisfiability. Although it is not competitive with state-of-the-art SAT solvers, NeuroSAT can solve problems that are substantially larger and more difficult than it ever saw during training by simply running for more iterations. Moreover, NeuroSAT generalizes to novel distributions; after training only on random SAT problems, at test time it can solve SAT problems encoding graph coloring, clique detection, dominating set, and vertex cover problems, all on a range of distributions over small random graphs.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑