arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.00276math.OCcs.CRcs.LGcs.SYeess.SY
收藏

稀疏扰动或半遗忘攻击下参数化非线性系统辨识问题的精确恢复保证

Exact Recovery Guarantees for Parameterized Nonlinear System Identification Problem under Sparse Disturbances or Semi-Oblivious Attacks

University of California, Berkeley(加州大学伯克利分校);Northeastern University(东北大学)

Haixiang Zhang, Baturalp Yalcin, Javad Lavaei, Eduardo D. Sontag

AI总结:

针对稀疏扰动或半遗忘攻击下的参数化非线性系统辨识问题,提出LASSO型非光滑估计器,给出其良定性与全局解唯一性条件,实现通用扰动模型下的有限时间精确恢复,拓展了现有理论适用范围。

摘要:

在这项工作中,我们研究通过基函数对动力学进行参数化来学习非线性动力系统的问题。我们假设每个时间步都有任意概率$p$的扰动发生,该概率用于建模扰动向量随时间变化的稀疏程度。这些扰动服从任意的未知概率分布,只要满足零均值假设,该分布可以依赖于过去的扰动。本文的主要目标是在有限时间内学习系统动力学,并分析作为$p$的函数的样本复杂度。为实现这一目标,我们研究了一种LASSO型非光滑估计器,并给出了其良定性以及底层优化问题全局解唯一性的充要条件。随后,我们在基函数有界性和Lipschitz连续性两种不同条件下,给出了该估计器的精确恢复保证。我们证明,即使$p$趋近于1,也能以高概率实现有限时间精确恢复。现有研究主要关注独立同分布(i.i.d.)扰动,且仅给出系统学习的渐近保证,与以往工作不同,本研究首次在高度通用的扰动模型下对非线性动力系统进行了有限时间分析。我们的框架允许扰动存在时间相关性,并且可适配半遗忘对抗攻击,极大拓宽了现有理论结果的适用范围。

英文摘要:

In this work, we study the problem of learning a nonlinear dynamical system by parameterizing its dynamics using basis functions. We assume that disturbances occur at each time step with an arbitrary probability $p$, which models the sparsity level of the disturbance vectors over time. These disturbances are drawn from an arbitrary, unknown probability distribution, which may depend on past disturbances, provided that it satisfies a zero-mean assumption. The primary objective of this paper is to learn the system's dynamics within a finite time and analyze the sample complexity as a function of $p$. To achieve this, we examine a LASSO-type non-smooth estimator, and establish necessary and sufficient conditions for its well-specifiedness and the uniqueness of the global solution to the underlying optimization problem. We then provide exact recovery guarantees for the estimator under two distinct conditions: boundedness and Lipschitz continuity of the basis functions. We show that finite-time exact recovery is achieved with high probability, even when $p$ approaches 1. Unlike prior works, which primarily focus on independent and identically distributed (i.i.d.) disturbances and provide only asymptotic guarantees for system learning, this study presents the first finite-time analysis of nonlinear dynamical systems under a highly general disturbance model. Our framework allows for possible temporal correlations in the disturbances and accommodates semi-oblivious adversarial attacks, significantly broadening the scope of existing theoretical results.

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。

↑