activity
20242026
collaborators

7 papers

cs.CV2026

On the explainability of max-plus neural networks

Ikhlas Enaieh, Olivier Fercoq, García Ángel

We investigate the explanability properties of the recently proposed linear-min-max neural networks. At initialization, they can be interpreted as k-medoids with the infinity norm…

stat.ML2026

Exploiting Subgradient Sparsity in Max-Plus Neural Networks

Ikhlas Enaieh, Olivier Fercoq

Deep Neural Networks are powerful tools for solving machine learning problems, but their training often involves dense and costly parameter updates. In this work, we use a novel Ma…

cs.SD2025

Harmonic-Percussive Disentangled Neural Audio Codec for Bandwidth Extension

Benoît Giniès, Xiaoyu Bie, Olivier Fercoq +1

Bandwidth extension, the task of reconstructing the high-frequency components of an audio signal from its low-pass counterpart, is a long-standing problem in audio processing. Whil…

math.OC2025

Proximal gradient descent on the smoothed duality gap to solve saddle point problems

Olivier Fercoq

In this paper, we minimize the self-centered smoothed gap, a recently introduced optimality measure, in order to solve convex-concave saddle point problems. The self-centered smoot…

cs.SD2025

Soft Disentanglement in Frequency Bands for Neural Audio Codecs

Benoit Ginies, Xiaoyu Bie, Olivier Fercoq +1

In neural-based audio feature extraction, ensuring that representations capture disentangled information is crucial for model interpretability. However, existing disentanglement me…

math.OC2025

Primal-Dual Coordinate Descent for Nonconvex-Nonconcave Saddle Point Problems Under the Weak MVI Assumption

Iyad Walwil, Olivier Fercoq

We introduce two novel primal-dual algorithms for addressing nonconvex, nonconcave, and nonsmooth saddle point problems characterized by the weak Minty Variational Inequality (MVI)…