hiw3c 日报精选
arXiv cs.AI/CL/LG 网页快照

Hyperlyve:深度ReLU网络的并行枚举与精确Lyapunov稳定性验证

原文标题 · Hyperlyve: Parallelized Enumeration and Exact Lyapunov Stability Certification for Deep ReLU Networks

作者: Brian Yarbrough, Jesse Wayment, Jingbo Wang | 我们介绍Hyperlyve(超平面划分李雅普诺夫验证与枚举),这是一种用于证明非线性动力系统渐近稳定的框架,包括那些带有神经网络控制器的系统。Hyperlyve在反例引导的归纳合成(CEGIS)循环中学习并形式证明连续分段仿射(CPA)神经李雅普诺夫函数。Hyperlyve的关键在于

来源:arXiv cs.AI/CL/LG · arxiv.org

正文为英文,可一键机器翻译(仅首次需要等待)

Electrical Engineering and Systems Science > Systems and Control

Title: Hyperlyve: Parallelized Enumeration and Exact Lyapunov Stability Certification for Deep ReLU Networks

Abstract: We introduce Hyperlyve (Hyperplane Partitioned Lyapunov Verification and Enumeration), a framework for proving the asymptotic stability of nonlinear dynamical systems, including those with neural network controllers. Hyperlyve learns and formally certifies continuous piecewise-affine (CPA) neural Lyapunov functions within a counterexample-guided inductive synthesis (CEGIS) loop. Hyperlyve's key innovation is a parallel algorithm that enumerates the hyperplane arrangement formed by the ReLU activations of deep networks and certifies that Lyapunov conditions hold within each polyhedral region. We derive sound and complete regional tests to verify the asymptotic stability of the exact smooth dynamics (rather than a piecewise-linear approximation) within a compact domain of interest. Furthermore, we formally characterize the computational complexity of the CPA neural Lyapunov verification problem as co-NP-complete, filling a key gap in the literature. Empirical results demonstrate that Hyperlyve enumerates ReLU networks over 150-times faster than competing tools, which contributes to Hyperlyve proving the asymptotic stability of systems that are currently intractable for state-of-the-art verifiers.

Submission history

Access Paper:

Current browse context:

References & Citations

BibTeX formatted citation

Bookmark

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs .