We survey the adversarial robustness of neural networks from the perspective of Lipschitz
calculus in a unifying fashion by expressing models, attacks and safety guarantees—that is …

Chordal and factor-width decomposition methods for semidefinite programming and
polynomial optimization have recently enabled the analysis and control of large-scale linear …

In the past decade, deep learning became the prevalent methodology for predictive
modeling thanks to the remarkable accuracy of deep neural networks in tasks such as …

This work proposes a new moment-SOS hierarchy, called CS-TSSOS, for solving large-
scale sparse polynomial optimization problems. Its novelty is to exploit simultaneously …

This work is a follow-up and a complement to [J. Wang, V. Magron and JB Lasserre, preprint,
arxiv: 1912.08899, 2019] where the TSSOS hierarchy was proposed for solving polynomial …

To improve the robustness of deep classifiers against adversarial perturbations, many
approaches have been proposed, such as designing new architectures with better …

It is promising to solve linear inverse problems by unfolding iterative algorithms (eg, iterative
shrinkage thresholding algorithm (ISTA)) as deep neural networks (DNNs) with learnable …

Lipschitz constant estimation plays an important role in understanding generalization,
robustness, and fairness in deep learning. Unlike naive bounds based on the network …

This article introduces a novel approach for building a robust Automatic Gesture Recognition
system based on Surface Electromyographic (sEMG) signals, acquired at the forearm level …

This article focuses on optimization of polynomials in noncommuting variables, while taking
into account sparsity in the input data. A converging hierarchy of semidefinite relaxations for …