Scalable Incremental Robustness Analysis of Neural Network Feedback Systems

2026-09-18

AI Summary

本文提出一种结合结构分解与Lipschitz常数估计的可扩展框架，用于分析含高维神经网络反馈系统的鲁棒稳定性及性能，降低了保守性。

Abstract

Semidefinite programming (SDP) certificates for feedback systems containing deep neural networks (NNs) typically scale with the total number of neurons, whereas small-gain tests are scalable but can be highly conservative. This paper develops a unified and scalable framework for incremental robust stability and performance analysis of feedback interconnections involving high-dimensional NNs and unmodeled dynamics. By combining a structured decomposition of the full-order SDP condition with scalable Lipschitz constant estimation algorithms, we derive reduced verification conditions that certify incremental convergence and incremental $\ell_2$-gain bounds. The dimensions of the resulting control-analysis linear matrix inequalities (LMIs) depend only on the widths of the last two network layers and are \textit{independent of network depth}. The framework preserves the coupling between the plant and the NN, with the incremental small-gain condition recovered as a special case. To further reduce conservatism, we develop a multi-round alternating update scheme that iteratively refines the coupling variables while preserving scalability. Numerical experiments show that the proposed framework achieves state-of-the-art incremental $\ell_2$-gain bounds for large-scale NN feedback systems.

Problem

• neural networks
• feedback systems
• scalability
• robustness analysis
• incremental stability

Innovation

• Scalable Incremental Robustness
• Neural Network Feedback Systems
• Structured Decomposition
• Lipschitz Constant Estimation
• Reduced Verification Conditions