A A
en
Deutsch
English
Menü
Home Members Roux

Roux, Christophe

Christophe Roux

Contact

Position
Staff
Room
3107
Phone
+49 30 84185-286
Email
Email
Website
Personal Homepage
Division
Mathematical Algorithmic Intelligence
Department
AI in Society, Science and Technology
Group
Interactive Optimization and Learning

Publications

2026
A Free Lunch in LLM Compression: Revisiting Retraining after Pruning Advances in Neural Information Processing Systems, Vol.39, 2026 (accepted for publication) Moritz Wagner, Christophe Roux, Max Zimmer, Sebastian Pokutta BibTeX
arXiv
Curvature-Dependent Lower Bounds for Frank-Wolfe Advances in Neural Information Processing Systems, Vol.39, 2026 (accepted for publication) Jannis Halbey, Christophe Roux, Sebastian Pokutta BibTeX
arXiv
From Associations to Activations: Comparing Behavioral and Hidden-State Semantic Geometry in LLMs Proceedings of the 43rd International Conference on Machine Learning, Vol.306, Proceedings of Machine Learning Research, 2026 Louis Schiekiera, Max Zimmer, Christophe Roux, Sebastian Pokutta, Fritz Günther BibTeX
arXiv
LinearPFN: Amortized Variable Selection for Linear Models with Interactions 2026 Louis Schiekiera, Max Zimmer, Christophe Roux, Manuel Arnold, Sebastian Pokutta, Fritz Günther BibTeX
arXiv
Lower Bounds for Frank-Wolfe on Strongly Convex Sets Proceedings of the 43rd International Conference on Machine Learning, Vol.306, Proceedings of Machine Learning Research, 2026 Jannis Halbey, Daniel Deza, Max Zimmer, Christophe Roux, Bartolomeo Stellato, Sebastian Pokutta BibTeX
arXiv
Restart and Adaptive Acceleration in Stochastic Gradient Methods 2026 Ali Elhishi, Christophe Roux, Alexandre d'Aspremont BibTeX
arXiv
The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning 2026 Max Zimmer, Nico Pelleriti, Christophe Roux, Sebastian Pokutta BibTeX
arXiv
The KV-Surgeon: Compensation-Aware Offline KV-Cache Compaction 2026 Moritz Wagner, Christophe Roux, Max Zimmer, Sebastian Pokutta BibTeX
arXiv
2025
Accelerated Methods for Riemannian Min-Max Optimization Ensuring Bounded Geometric Penalties Proceedings of The 28th International Conference on Artificial Intelligence and Statistics, pp. 280-288, Vol.258, Proceedings of Machine Learning Research, 2025 David Martínez-Rubio, Christophe Roux, Christopher Criscitiello, Sebastian Pokutta BibTeX
arXiv
Don't Be Greedy, Just Relax! Pruning LLMs via Frank-Wolfe 2025 Christophe Roux, Max Zimmer, Alexandre d'Aspremont, Sebastian Pokutta BibTeX
arXiv
Implicit Riemannian optimism with applications to min-max problems Proceedings of the 42nd International Conference on Machine Learning, pp. 52139-52172, Vol.267, Proceedings of Machine Learning Research, 2025 Christophe Roux, David Martínez-Rubio, Sebastian Pokutta BibTeX
arXiv
On the byzantine-resilience of distillation-based federated learning International Conference on Learning Representations 2025, 2025 Christophe Roux, Max Zimmer, Sebastian Pokutta BibTeX
arXiv
SparseSwaps: Tractable LLM Pruning Mask Refinement at Scale 2025 Max Zimmer, Christophe Roux, Moritz Wagner, Deborah Hendrych, Sebastian Pokutta BibTeX
arXiv
2024
Convergence and Trade-Offs in Riemannian Gradient Descent and Riemannian Proximal Point Proceedings of the 41st International Conference on Machine Learning, pp. 34920-34948, Vol.235, Proceedings of Machine Learning Research, 2024 David Martínez-Rubio, Christophe Roux, Sebastian Pokutta BibTeX
arXiv
2021
Efficient Online-Bandit Strategies for Minimax Learning Problems 2021 Christophe Roux, Elias Wirth, Sebastian Pokutta, Thomas Kerdreux BibTeX
arXiv
Linear Bandits on Uniformly Convex Sets Journal of Machine Learning Research, 22(284), pp. 1-23, 2021 Thomas Kerdreux, Christophe Roux, Alexandre d'Aspremont, Sebastian Pokutta BibTeX
arXiv