5 papers
On the Comparison of Optimizers for Imbalanced Learning
Cl{é}ment Lezane, Fran{\c c}ois Bachoc, J{é}r{ô}me Bolte +1
Data imbalance is pervasive in machine learning, from rare words and anomalies to underrepresented patterns in heterogeneous or cross-tabulated data. We study idealized optimizers…
Acceleration for Affine-coupling problems
Clement Lezane, Sophie Langer, Wouter M. Koolen
Saddle-point problems play an important role in modern machine learning, including robust optimization and algorithmic fairness. We investigate structured convex--concave minimax p…
Differentially Private Algorithms for Linear Queries via Stochastic Convex Optimization
Giorgio Micali, Clement Lezane, Annika Betken
This article establishes a method to answer a finite set of linear queries on a given dataset while ensuring differential privacy. To achieve this, we formulate the corresponding t…
Oblivious Stochastic Composite Optimization
Clément Lezane, Alexandre d'Aspremont
In stochastic convex optimization problems, most existing adaptive methods rely on prior knowledge about the diameter bound when the smoothness or the Lipschitz constant is unk…
Optimal Algorithms for Stochastic Complementary Composite Minimization
Alexandre d'Aspremont, Cristóbal Guzmán, Clément Lezane
Inspired by regularization techniques in statistics and machine learning, we study complementary composite minimization in the stochastic setting. This problem corresponds to the m…