3 papers
math.OC2026
Relax and Follow: L0-Path Computation with L0-Bregman Relaxations
Mhamed Essafri, Luca Calatroni, Emmanuel Soubies
This work introduces L0PathBrex, a novel method for estimating the solution path of L0-regularized problems through the use of L0 Bregman relaxations (B-rex). Recently introduced a…
math.OC2025
Proximal Operators of Sorted Nonconvex Penalties
Anne Gagneux, Mathurin Massias, Emmanuel Soubies
This work studies the problem of sparse signal recovery with automatic grouping of variables. To this end, we investigate sorted nonsmooth penalties as a regularization approach fo…
cs.LG2025
Convexity in ReLU Neural Networks: beyond ICNNs?
Anne Gagneux, Mathurin Massias, Emmanuel Soubies +1
Convex functions and their gradients play a critical role in mathematical imaging, from proximal optimization to Optimal Transport. The successes of deep learning has led many to u…