提出可复用安全证书的框架，让自适应系统在状态变化时节省大量重验证计算。
VeRecycle: Reclaiming Guarantees from Probabilistic Certificates for Stochastic Dynamical Systems after Change
- 通过形式化方法复用已有概率安全证书，仅需局部更新
- 实验显示计算量大幅降低，且保证效果接近重新认证
- 适合需要快速响应动态变化的自动驾驶等实时控制系统
现实世界的自主系统面临多种不确定性。概率神经李雅普诺夫认证是验证非线性随机动力系统安全性的有力方法。当系统遭遇模型外的变化（如未识别障碍物）时，需将原有概率证书迁移至新动态。然而，现有方法即使变化仅局限于状态空间中已知区域，也需完全重新认证，对神经网络证书而言成本极高。本文提出首个针对离散时间随机动力系统的正式复用框架——VeRecycle。该框架能在系统动态仅在特定状态子集发生改变时，高效重用原有概率证书。我们提供了通用理论依据与算法实现。实验表明，在多种场景下，VeRecycle显著降低计算开销，同时保持与完整重认证相当的概率安全保证，适用于组合式神经控制任务。
原文摘要 · Abstract (English)
Autonomous systems operating in the real world encounter a range of uncertainties. Probabilistic neural Lyapunov certification is a powerful approach to proving safety of nonlinear stochastic dynamical systems. When faced with changes beyond the modeled uncertainties, e.g., unidentified obstacles, probabilistic certificates must be transferred to the new system dynamics. However, even when the changes are localized in a known part of the state space, state-of-the-art requires complete re-certification, which is particularly costly for neural certificates. We introduce VeRecycle, the first framework to formally reclaim guarantees for discrete-time stochastic dynamical systems. VeRecycle efficiently reuses probabilistic certificates when the system dynamics deviate only in a given subset of states. We present a general theoretical justification and algorithmic implementation. Our experimental evaluation shows scenarios where VeRecycle both saves significant computational effort and achieves competitive probabilistic guarantees in compositional neural control.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。