7 papers
On the explainability of max-plus neural networks
Ikhlas Enaieh, Olivier Fercoq, GarcÃa Ãngel
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…
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…
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…
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…
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…
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)…