mlsanityData to 14 Oct 2026

Convex neural network synthesis for robustness in the 1-norm

arXiv 2405.19029 ↗First posted 29 May 2024eess.SY cs.AI cs.SYcited by 0

Not on the map. Why?

Abstract (arXiv)

With neural networks being used to control safety-critical systems, they increasingly have to be both accurate (in the sense of matching inputs to outputs) and robust. However, these two properties are often at odds with each other and a trade-off has to be navigated. To address this issue, this paper proposes a method to generate an approximation of a neural network which is certifiably more robust. Crucially, the method is fully convex and posed as a semi-definite programme. An application to robustifying model predictive control is used to demonstrate the results. The aim of this work is to introduce a method to navigate the neural network robustness/accuracy trade-off.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 27 references that are in the map. First posted on arXiv 29 May 2024.

Builds on

17 of 27 references.

References · 17

  1. 2019Deep Equilibrium Modelscited by 615
  2. 2019Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networkscited by 293
  3. 2019Implicit Deep Learningcited by 124
  4. 2020Training robust neural networks using Lipschitz boundscited by 99
  5. 2023Direct Parameterization of Lipschitz-Bounded Deep Networkscited by 51
  6. 2021Recurrent Equilibrium Networks: Flexible Dynamic Models with Guaranteed Stability and Robustnesscited by 45
  7. 2022Deep Equilibrium Approaches to Diffusion Modelscited by 42
  8. 2022A Quantitative Geometric Approach to Neural-Network Smoothnesscited by 16
  9. 2022Neural System Level Synthesis: Learning over All Stabilizing Policies for Nonlinear Systemscited by 11
  10. 2022Sparse Polynomial Optimisation for Neural Network Verificationcited by 8
  11. 2022Synthesis of Stabilizing Recurrent Equilibrium Network Controllerscited by 8
  12. 2021Linear systems with neural network nonlinearities: Improved stability analysis via acausal Zames-Falb multiplierscited by 6
5 more
  1. 2022Stability of Non-linear Neural Feedback Loops using Sum of Squarescited by 6
  2. 2022Bounding the difference between model predictive control and neural networkscited by 4
  3. 2020Robust error bounds for quantised and pruned neural networkscited by 3
  4. 2021Reduced-Order Neural Network Synthesis with Robustness Guaranteescited by 3
  5. 2024Mapping back and forth between model predictive control and neural networkscited by 1

Built on by

Not cited yet.