208 citations · 1.7k across the 69 of their papers we have counts for
3 papers · 1 filter
General risk measures for robust machine learning
Emilie Chouzenoux, Henri Gérard, Jean-Christophe Pesquet
A wide array of machine learning problems are formulated as the minimization of the expectation of a convex loss function on some parameter space. Since the probability distributio…
Preconditioned P-ULA for Joint Deconvolution-Segmentation of Ultrasound Images -- Extended Version
Corbineau Marie-Caroline, Kouamé Denis, Chouzenoux Emilie +2
Joint deconvolution and segmentation of ultrasound images is a challenging problem in medical imaging. By adopting a hierarchical Bayesian model, we propose an accelerated Markov c…
Lipschitz Certificates for Layered Network Structures Driven by Averaged Activation Operators
Patrick L. Combettes, Jean-Christophe Pesquet
Obtaining sharp Lipschitz constants for feed-forward neural networks is essential to assess their robustness in the face of perturbations of their inputs. We derive such constants…