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 2209.09400cs.LGcs.SYeess.SYstat.ML
收藏

具有两级格型神经网络控制器的LTI系统的多项式时间可达性

Polynomial-Time Reachability for LTI Systems with Two-Level Lattice Neural Network Controllers

University of California, Irvine(加州大学欧文分校)

James Ferlez, Yasser Shoukry

摘要:

本文研究了线性定常系统(LTI)在整流线性单元(ReLU)两级格型(TLL)神经网络(NN)控制器控制下的可达集的计算复杂性。特别是,我们表明,对于这样的系统和控制器,它是可以计算的确切的一步可达集在多项式时间的大小的TLL NN控制器(神经元的数量)。此外,我们表明,一个紧密的限界框的可达集是可计算的,通过两个多项式时间的方法:一个多项式复杂性的大小TLL和其他多项式复杂性的Lipschitz常数的控制器和其他问题的参数。最后,我们提出了一个务实的算法,自适应地结合了(半)精确可达性和近似可达性,我们称之为L-TLLBox的好处。我们评估L-TLLBox与最先进的NN控制器可达性工具的经验比较。在我们的实验中,L-TLLBox在相同的网络/系统上完成可达性分析的速度比这个工具快5000倍,同时产生的可达性盒的面积是它的0.08到1.42倍。

英文摘要:

In this paper, we consider the computational complexity of bounding the reachable set of a Linear Time-Invariant (LTI) system controlled by a Rectified Linear Unit (ReLU) Two-Level Lattice (TLL) Neural Network (NN) controller. In particular, we show that for such a system and controller, it is possible to compute the exact one-step reachable set in polynomial time in the size of the TLL NN controller (number of neurons). Additionally, we show that a tight bounding box of the reachable set is computable via two polynomial-time methods: one with polynomial complexity in the size of the TLL and the other with polynomial complexity in the Lipschitz constant of the controller and other problem parameters. Finally, we propose a pragmatic algorithm that adaptively combines the benefits of (semi-)exact reachability and approximate reachability, which we call L-TLLBox. We evaluate L-TLLBox with an empirical comparison to a state-of-the-art NN controller reachability tool. In our experiments, L-TLLBox completed reachability analysis as much as 5000x faster than this tool on the same network/system, while producing reach boxes that were from 0.08 to 1.42 times the area.

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。

↑