Abstract
This paper analyzes the internal stability of a discrete-time feedback system with rectified linear unit (ReLU) nonlinearity. This feedback system is motivated by recurrent neural networks. We first review existing static quadratic constraints (QCs) for slope-restricted nonlinearities. Next, we derive hard integral quadratic constraints (IQCs) for scalar ReLU by using finite impulse filters and structured matrices. These IQCs are combined with a dissipation inequality leading to an LMI condition that certifies internal stability. We show that our new dynamic IQCs for ReLU are a superset of the well-known Zames-Falb IQCs specified for slope-restricted nonlinearities. Numerical results show that the proposed hard IQCs give less conservative stability margins than Zames-Falb multipliers and prior static QC methods, sometimes dramatically so.
| Original language | English (US) |
|---|---|
| Title of host publication | 2026 American Control Conference, ACC 2026 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 1664-1669 |
| Number of pages | 6 |
| ISBN (Electronic) | 9798331593810 |
| State | Published - 2026 |
| Event | 2026 American Control Conference, ACC 2026 - New Orleans, United States Duration: May 26 2026 → May 29 2026 |
Publication series
| Name | Proceedings of the American Control Conference |
|---|---|
| ISSN (Print) | 0743-1619 |
Conference
| Conference | 2026 American Control Conference, ACC 2026 |
|---|---|
| Country/Territory | United States |
| City | New Orleans |
| Period | 5/26/26 → 5/29/26 |
Bibliographical note
Publisher Copyright:© 2026 AACC.
Fingerprint
Dive into the research topics of 'Discrete-Time Stability Analysis of ReLU Feedback Systems via Integral Quadratic Constraints'. Together they form a unique fingerprint.Cite this
- APA
- Standard
- Harvard
- Vancouver
- Author
- BIBTEX
- RIS