86 citations · 685 across the 45 of their papers we have counts for
51 papers
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…
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-passed counterpart, is a long-standing problem in audio processing. In…
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)…
Defining Lyapunov functions as the solution of a performance estimation saddle point problem
Olivier Fercoq
In this paper, we reinterpret quadratic Lyapunov functions as solutions to a performance estimation saddle point problem. This allows us to automatically detect the existence of su…
Using Random Codebooks for Audio Neural AutoEncoders
Benoît Giniès, Xiaoyu Bie, Olivier Fercoq +1
Latent representation learning has been an active field of study for decades in numerous applications. Inspired among others by the tokenization from Natural Language Processing an…
Monitoring the Convergence Speed of PDHG to Find Better Primal and Dual Step Sizes
Olivier Fercoq
Primal-dual algorithms for the resolution of convex-concave saddle point problems usually come with one or several step size parameters. Within the range where convergence is guara…
The Smoothed Duality Gap as a Stopping Criterion
Iyad Walwil, Olivier Fercoq
We optimize the running time of the primal-dual algorithms by optimizing their stopping criteria for solving convex optimization problems under affine equality constraints, which m…
Escaping limit cycles: Global convergence for constrained nonconvex-nonconcave minimax problems
Thomas Pethick, Puya Latafat, Panagiotis Patrinos +2
This paper introduces a new extragradient-type algorithm for a class of nonconvex-nonconcave minimax problems. It is well-known that finding a local solution for general minimax pr…
Solving stochastic weak Minty variational inequalities without increasing batch size
Thomas Pethick, Olivier Fercoq, Puya Latafat +2
This paper introduces a family of stochastic extragradient-type algorithms for a class of nonconvex-nonconcave problems characterized by the weak Minty variational inequality (MVI)…
Quadratic error bound of the smoothed gap and the restarted averaged primal-dual hybrid gradient
Olivier Fercoq
We study the linear convergence of the primal-dual hybrid gradient method. After a review of current analyses, we show that they do not explain properly the behavior of the algorit…
Faster One-Sample Stochastic Conditional Gradient Method for Composite Convex Minimization
Gideon Dresdner, Maria-Luiza Vladarean, Gunnar Rätsch +3
We propose a stochastic conditional gradient method (CGM) for minimizing convex finite-sum objectives formed as a sum of smooth and non-smooth terms. Existing CGM variants for this…
Screening Rules and its Complexity for Active Set Identification
Eugene Ndiaye, Olivier Fercoq, Joseph Salmon
Screening rules were recently introduced as a technique for explicitly identifying active structures such as sparsity, in optimization problem arising in machine learning. This has…
Random extrapolation for primal-dual coordinate descent
Ahmet Alacaoglu, Olivier Fercoq, Volkan Cevher
We introduce a randomly extrapolated primal-dual coordinate descent method that adapts to sparsity of the data matrix and the favorable structures of the objective function. Our me…
Improved Optimistic Algorithms for Logistic Bandits
Louis Faury, Marc Abeille, Clément Calauzènes +1
The generalized linear bandit framework has attracted a lot of attention in recent years by extending the well-understood linear setting and allowing to model richer reward structu…
Scalable Semidefinite Programming
Alp Yurtsever, Joel A. Tropp, Olivier Fercoq +2
Semidefinite programming (SDP) is a powerful framework from convex optimization that has striking potential for data science applications. This paper develops a provably correct ra…
Linear convergence of dual coordinate descent on non-polyhedral convex problems
Ion Necoara, Olivier Fercoq
This paper deals with constrained convex problems, where the objective function is smooth strongly convex and the feasible set is given as the intersection of a large number of clo…
On the convergence of stochastic primal-dual hybrid gradient
Ahmet Alacaoglu, Olivier Fercoq, Volkan Cevher
In this paper, we analyze the recently proposed stochastic primal-dual hybrid gradient (SPDHG) algorithm and provide new theoretical results. In particular, we prove almost sure co…
Almost surely constrained convex optimization
Olivier Fercoq, Ahmet Alacaoglu, Ion Necoara +1
We propose a stochastic gradient framework for solving stochastic composite convex optimization problems with (possibly) infinite number of linear inclusion constraints that need t…
Improving Evolutionary Strategies with Generative Neural Networks
Louis Faury, Clement Calauzenes, Olivier Fercoq +1
Evolutionary Strategies (ES) are a popular family of black-box zeroth-order optimization algorithms which rely on search distributions to efficiently optimize a large variety of ob…
A Conditional Gradient-Based Augmented Lagrangian Framework
Alp Yurtsever, Olivier Fercoq, Volkan Cevher
This paper considers a generic convex minimization template with affine constraints over a compact domain, which covers key semidefinite programming applications. The existing cond…
Stochastic Frank-Wolfe for Composite Convex Minimization
Francesco Locatello, Alp Yurtsever, Olivier Fercoq +1
A broad class of convex optimization problems can be formulated as a semidefinite program (SDP), minimization of a convex function over the positive-semidefinite cone subject to so…