arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.07652cs.LGcs.SYeess.SYmath.OCstat.ML
收藏

部分观测双线性动力系统的有限样本辨识

Finite Sample Identification of Partially Observed Bilinear Dynamical Systems

Cornell(康奈尔大学);MIT(麻省理工学院);U Washington(华盛顿大学)

Yahya Sattar, Yassir Jedra, Maryam Fazel, Sarah Dean

AI总结:

针对部分观测双线性动力系统的辨识难题,提出基于重尾非线性协变量回归的类马尔可夫参数学习算法,给出一致稳定性下的高概率误差界,通过合成数据实验验证了结论。

摘要:

我们研究从含噪输入输出数据中学习部分观测双线性动力系统(BLDS)实现的问题。给定单条输入输出样本轨迹,我们给出了学习系统类马尔可夫参数的有限时间分析,由此可得到双线性系统的平衡实现。我们的双线性系统辨识算法通过将输出回归到高度相关、非线性且重尾的协变量,来学习系统的类马尔可夫参数。此外,BLDS的稳定性取决于用于激励系统的输入序列。这些部分观测双线性动力系统特有的性质,给我们学习未知动力学的算法分析带来了重大挑战。我们解决了这些挑战,并在一致稳定性假设下给出了辨识算法的高概率误差界。我们的分析揭示了影响学习精度和样本复杂度的系统理论量。最后,我们用合成数据开展了数值实验以验证这些结论。

英文摘要:

We consider the problem of learning a realization of a partially observed bilinear dynamical system (BLDS) from noisy input-output data. Given a single trajectory of input-output samples, we provide a finite time analysis for learning the system's Markov-like parameters, from which a balanced realization of the bilinear system can be obtained. Our bilinear system identification algorithm learns the system's Markov-like parameters by regressing the outputs to highly correlated, nonlinear, and heavy-tailed covariates. Moreover, the stability of BLDS depends on the sequence of inputs used to excite the system. These properties, unique to partially observed bilinear dynamical systems, pose significant challenges to the analysis of our algorithm for learning the unknown dynamics. We address these challenges and provide high probability error bounds on our identification algorithm under a uniform stability assumption. Our analysis provides insights into system theoretic quantities that affect learning accuracy and sample complexity. Lastly, we perform numerical experiments with synthetic data to reinforce these insights.

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。

↑