Thomas Boudou — accepted AI-conference papers

2026

Optimal Transport under Group Fairness Constraints

Linus Bleistein, Mathieu Dagréou, Francisco Andrade, Thomas Boudou, Aurélien Bellet

ICML 2026spotlight

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 fairness requiring that the probability of matching two individuals from any two given groups in the OT plan satisfies a …

Cited by 0 Source ↗Scholar ↗

2026

Tight Stability Bounds for Robust Distributed Learning: Byzantine Failures Hurt Generalization More than Data Poisoning

Thomas Boudou, Batiste Le Bars, Nirupam Gupta, Aurélien Bellet

ICML 2026poster

Robust distributed learning algorithms aim to maintain reliable performance despite the presence of misbehaving workers. Such misbehaviors are commonly modeled as *Byzantine failures*, allowing arbitrarily corrupted communication, or as *data poisoning*, a weaker form of corruption restricted to loc…

Cited by 0 Source ↗Scholar ↗