In this work we develop a mathematic and algo rithmic framework for data-driven stability analysis of black box switching systems by using adaptive sampling and on line optimization. Our algorithm learns the optimal sam pling strategy to build more accurate stability guarantees with fewer sampling points. This work is an extension of [ l], where an algorithm is presented to bound the Joint Spec tral Radius (JSR) [2] of an unknown switched linear system within some probability from a finite number of trajectories.
Farjadnia, M., Wang, Z., & Jungers, R. (2019). Stability Analysis of Data Driven Complex Systems. 38th Benelux Meeting on Systems and Control, Lommel, Belgium. https://hdl.handle.net/2078.5/252222