4 papers
Detectability in Diversity: Improved Canary Crafting for Privacy Auditing in One Run
Mathieu Dagréou, Aurélien Bellet
Privacy auditing aims to empirically assess privacy leakage in machine learning models using membership inference attacks (MIAs), and to derive lower bounds on differential privacy…
Optimal Transport under Group Fairness Constraints
Linus Bleistein, Mathieu Dagréou, Francisco Andrade +2
Ensuring fairness in matching algorithms is a key challenge in allocating scarce resources and positions. Focusing on Optimal Transport (OT), we introduce a novel notion of group f…
A Lower Bound and a Near-Optimal Algorithm for Bilevel Empirical Risk Minimization
Mathieu Dagréou, Thomas Moreau, Samuel Vaiter +1
Bilevel optimization problems, which are problems where two optimization problems are nested, have more and more applications in machine learning. In many practical cases, the uppe…
A framework for bilevel optimization that enables stochastic and global variance reduction algorithms
Mathieu Dagréou, Pierre Ablin, Samuel Vaiter +1
Bilevel optimization, the problem of minimizing a value function which involves the arg-minimum of another function, appears in many areas of machine learning. In a large scale emp…