Robust and structure exploiting optimisation algorithms: an integral quadratic constraint approach

S Michalowsky, C Scherer… - International Journal of …, 2021 - Taylor & Francis
We consider the problem of analysing and designing gradient-based discrete-time
optimisation algorithms for a class of unconstrained optimisation problems having strongly …

Event-triggered neural network control using quadratic constraints for perturbed systems

C de Souza, A Girard, S Tarbouriech - Automatica, 2023 - Elsevier
This paper investigates the event-triggered control problem for perturbed systems under
neural network controllers. We propose a novel event-triggering mechanism, based on local …

Linear systems with neural network nonlinearities: Improved stability analysis via acausal Zames-Falb multipliers

P Pauli, D Gramlich, J Berberich… - 2021 60th IEEE …, 2021 - ieeexplore.ieee.org
In this paper, we analyze the stability of feedback interconnections of a linear time-invariant
system with a neural network nonlinearity in discrete time. Our analysis is based on …

A frequency-domain analysis of inexact gradient methods

O Gannot - Mathematical Programming, 2022 - Springer
We study robustness properties of some iterative gradient-based methods for strongly
convex functions, as well as for the larger class of functions with sector-bounded gradients …

Convex searches for discrete-time Zames–Falb multipliers

J Carrasco, WP Heath, J Zhang… - … on Automatic Control, 2019 - ieeexplore.ieee.org
In this article, we develop and analyze convex searches for Zames-Falb multipliers. We
present two different approaches: infinite impulse response (IIR) and finite impulse response …

On the exactness of a stability test for discrete-time Lur'e systems with slope-restricted nonlinearities

A Kharitenko, CW Scherer - IEEE Transactions on Automatic …, 2024 - ieeexplore.ieee.org
In this note it is shown that the famous multiplier absolute stability test of R. O'Shea, G.
Zames and P. Falb is necessary and sufficient if the set of Lur'e interconnections is lifted to a …

Local Lipschitz constant computation of ReLU-FNNs: Upper bound computation with exactness verification

Y Ebihara, X Dai, T Yuno, V Magron… - 2024 European …, 2024 - ieeexplore.ieee.org
This paper is concerned with the computation of the local Lipschitz constant of feedforward
neural networks (FNNs) with activation functions being rectified linear units (ReLUs). The …

Stability analysis of piecewise affine systems with multi-model predictive control

P Petsagkourakis, WP Heath, C Theodoropoulos - Automatica, 2020 - Elsevier
We propose an input–output stability analysis for closed-loop systems of piece-wise affine
models under unstructured uncertainty and controlled by multi-model linear MPC with input …

l2 induced norm analysis of discrete-time LTI systems for nonnegative input signals and its application to stability analysis of recurrent neural networks

Y Ebihara, H Waki, V Magron, NHA Mai… - European Journal of …, 2021 - Elsevier
In this paper, we focus on the “positive” l 2 induced norm of discrete-time linear time-
invariant systems where the input signals are restricted to be nonnegative. To cope with the …

[HTML][HTML] On the necessity and sufficiency of discrete-time O'Shea–Zames–Falb multipliers

L Su, P Seiler, J Carrasco, SZ Khong - Automatica, 2023 - Elsevier
This paper considers the robust stability of a discrete-time Lurye system consisting of the
feedback interconnection between a linear system and a bounded and monotone …