arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.06136cs.LOcs.PLcs.SYeess.SY
收藏

基于神经网络的定量验证

Quantitative Verification with Neural Networks

University of Oxford(牛津大学);University of Birmingham(伯明翰大学)

Alessandro Abate, Alec Edwards, Mirco Giacobbe, Hashan Punchihewa, Diptarko Roy

AI总结:

本文提出利用神经网络计算概率过程在有限时间内命中目标条件的概率界,通过反例引导归纳合成循环验证证书的有效性,实现对随机程序和随机动力学模型的定量验证。

摘要:

我们提出了一种数据驱动的方法,用于随机程序和随机动力学模型的定量验证。我们的方法利用神经网络计算随机过程在有限时间内命中目标条件的概率的紧致且可信的界。该问题涵盖了从离散时间随机动力学模型的可达性和安全性分析,到概率程序的断言违反和终止分析。我们依赖神经网络表示超级鞅证书,通过反例引导归纳合成循环:我们训练神经证书,同时通过随机优化收紧概率界,然后通过可满足性模理论正式检查证书的有效性;如果收到反例,我们将其添加到样本集中并重复循环,直到有效性得到确认。我们在多样化的基准测试中展示了,得益于神经网络的表达能力,我们的方法在所有情况下都能产生更小或可比的概率界,且在现有符号方法无法触及的模型上取得成功。

英文摘要:

We present a data-driven approach to the quantitative verification of probabilistic programs and stochastic dynamical models. Our approach leverages neural networks to compute tight and sound bounds for the probability that a stochastic process hits a target condition within finite time. This problem subsumes a variety of quantitative verification questions, from the reachability and safety analysis of discrete-time stochastic dynamical models, to the study of assertion-violation and termination analysis of probabilistic programs. We rely on neural networks to represent supermartingale certificates that yield such probability bounds, which we compute using a counterexample-guided inductive synthesis loop: we train the neural certificate while tightening the probability bound over samples of the state space using stochastic optimisation, and then we formally check the certificate's validity over every possible state using satisfiability modulo theories; if we receive a counterexample, we add it to our set of samples and repeat the loop until validity is confirmed. We demonstrate on a diverse set of benchmarks that, thanks to the expressive power of neural networks, our method yields smaller or comparable probability bounds than existing symbolic methods in all cases, and that our approach succeeds on models that are entirely beyond the reach of such alternative techniques.

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。

↑