arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.10967cs.LG
收藏

学习测试:用于动态不稳定性检测的物理信息表示

Learning to Test: Latent Representation Learning for Dynamic Instability Detection

Carnegie Mellon University(卡内基梅隆大学);University of Minnesota(明尼苏达大学)

Minxing Zheng, Zewei Deng, Liyan Xie, Shixiang Zhu

AI总结:

本文提出一种面向测试的学习框架,用于在分布偏移下评估稳定性。通过学习物理信息的潜在表示,结合神经动力学替代体和不确定性校准,实现对随机约束动态系统的不稳定性检测。

摘要:

许多安全关键的科学和工程系统遵循微分代数方程(DAE),其动态行为受物理定律和可接受条件约束。在实践中,这些系统在随机变化的环境输入下运行,因此稳定性不是静态属性,而必须随着上下文分布的变化重新评估。然而,重复大规模DAE模拟在高维或实时设置中计算上是不可行的。本文提出了一种面向测试的学习框架,用于在分布偏移下评估稳定性。而不是重新估计物理参数或重复求解底层DAE,我们学习了具有上下文变量的物理信息潜在表示,该表示捕捉了与稳定性相关的结构,并被正则化到可处理的参考分布。在基线数据上训练的表示使部署时的安全监控可以表述为潜在空间中的分布假设检验,具有受控的I型错误。通过整合神经动力学替代体、不确定性意识校准和基于均匀性的测试,我们的方法提供了一种可扩展且统计上坚实的检测随机约束动态系统不稳定性风险的方法,而无需重复模拟。

英文摘要:

Stability assessment is central to safety-critical systems governed by differential-algebraic equations (DAEs), whose dynamics are constrained by physical laws and admissibility conditions. These systems operate under stochastically varying environmental inputs, so stability must be reassessed as the context distribution shifts, yet repeated large-scale DAE simulation is prohibitive in high-dimensional or real-time settings. We propose a test-oriented learning framework that tests a trajectory-level chance constraint from deployment contexts alone. Rather than re-estimating physical parameters or re-solving the DAE, we learn a latent representation from baseline context-trajectory data that retains stability-relevant information and is regularized toward a tractable reference distribution, and calibrate a latent discrepancy test over the composite safety null. We establish exact validity for oracle calibration and asymptotic validity for its empirical implementation under class-conditional latent invariance, and show that the guarantee degrades gracefully when this invariance holds only approximately. On simulated dynamical systems and a power-system real-world example, our approach strikes a balance between validity and power, whereas other baseline methods each fail in at least one regime. An ablation that injects controlled violations of the invariance assumption shows that decisions stay correct while the violation is below the safety margin, as the theory predicts.

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。

↑