publications

2026

1. Lower Bounds for Frank-Wolfe on Strongly Convex Sets

   Jannis Halbey, Daniel Deza, Max Zimmer, Christophe Roux, Bartolomeo Stellato, and Sebastian Pokutta

   arXiv CoRR, 2026

   arXiv
2. From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs

   Louis Schiekiera, Max Zimmer, Christophe Roux, Sebastian Pokutta, and Fritz Günther

   arXiv CoRR, 2026

   arXiv

2025

1. SparseSwaps: Tractable LLM Pruning Mask Refinement at Scale

   Max Zimmer, Christophe Roux, Moritz Wagner, Deborah Hendrych, and Sebastian Pokutta

   arXiv CoRR, 2025

   arXiv
2. Don’t Be Greedy, Just Relax! Pruning LLMs via Frank-Wolfe

   Christophe Roux^*, Max Zimmer^*, Alexandre d’Aspremont, and Sebastian Pokutta

   arXiv CoRR, 2025

   arXiv
3. Implicit Riemannian Optimism with Applications to Min-Max Problems

   Christophe Roux^*, David Martínez-Rubio^*, and Sebastian Pokutta

   ICML25 In Forty-second International Conference on Machine Learning, 2025

   arXiv
4. A Free Lunch in LLM Compression: Revisiting Retraining after Pruning

   Moritz Wagner, Christophe Roux, Max Zimmer, and Sebastian Pokutta

   arXiv CoRR, 2025

   arXiv
5. Accelerated Methods for Riemannian Min-Max Optimization Ensuring Bounded Geometric Penalties

   David Martínez-Rubio^*, Christophe Roux^*, Christopher Criscitiello, and Sebastian Pokutta

   AISTATS25 In International Conference on Artificial Intelligence and Statistics, 2025

   arXiv
6. On the Byzantine-Resilience of Distillation-Based Federated Learning

   Christophe Roux^*, Max Zimmer^*, and Sebastian Pokutta

   ICLR25 In The Thirteenth International Conference on Learning Representations, 2025

   arXiv Blog

2024

1. Convergence and Trade-Offs in Riemannian Gradient Descent and Riemannian Proximal Point

   David Martínez-Rubio^*, Christophe Roux^*, and Sebastian Pokutta

   ICML24 In Forty-first International Conference on Machine Learning, 2024

   arXiv

2021

1. Efficient Online-Bandit Strategies for Minimax Learning Problems

   Christophe Roux, Elias Samuel Wirth, Sebastian Pokutta, and Thomas Kerdreux

   arXiv CoRR, 2021

   arXiv
2. Linear Bandits on Uniformly Convex Sets

   Thomas Kerdreux, Christophe Roux, Alexandre d’Aspremont, and Sebastian Pokutta

   JMLR Journal of Machine Learning Research, 2021

   arXiv Blog