Christophe Roux

My research interests lie at the intersection of optimization and machine learning. In particular, I am interested in online optimization, federated learning and optimization on riemannian manifolds.

📬 Contact

office
Room 3107 at ZIB
e-mail
homepage
christopheroux.de
languages
German, English, and French

🎓 Curriculum vitae

since 2022
Member of BMS
since 2021
Researcher at ZIB
2021 to 2021
Research Assistant at ZIB
Jun 2021
M.Sc. in Scientific Computing at TUB
Feb 2018
B.Sc. in Engineering Science at TUB

đź“ť Publications and preprints

Preprints

  1. Roux, C., Zimmer, M., and Pokutta, S. (2024). On the Byzantine-resilience of Distillation-based Federated Learning. [arXiv]
    [BibTeX]
    @misc{2024_RouxZimmerPokutta_Byzantineresilience,
      archiveprefix = {arXiv},
      eprint = {2402.12265},
      primaryclass = {cs.LG},
      year = {2024},
      author = {Roux, Christophe and Zimmer, Max and Pokutta, Sebastian},
      title = {On the Byzantine-resilience of Distillation-based Federated Learning}
    }
  2. MartĂ­nez-Rubio, D., Roux, C., Criscitiello, C., and Pokutta, S. (2023). Accelerated Riemannian Min-Max Optimization Ensuring Bounded Geometric Penalties. [arXiv]
    [BibTeX]
    @misc{2023_MartinezrubioRouxCriscitielloPokutta_Riemannianminmax,
      archiveprefix = {arXiv},
      eprint = {2305.16186},
      primaryclass = {math.OC},
      year = {2023},
      author = {MartĂ­nez-Rubio, David and Roux, Christophe and Criscitiello, Christopher and Pokutta, Sebastian},
      title = {Accelerated Riemannian Min-Max Optimization Ensuring Bounded Geometric Penalties}
    }
  3. Roux, C., Wirth, E., Pokutta, S., and Kerdreux, T. (2021). Efficient Online-bandit Strategies for Minimax Learning Problems. [arXiv]
    [BibTeX]
    @misc{2021_RouxWirthPokuttaKerdreux_Onlinebanditminimax,
      archiveprefix = {arXiv},
      eprint = {2105.13939},
      primaryclass = {cs.LG},
      year = {2021},
      author = {Roux, Christophe and Wirth, Elias and Pokutta, Sebastian and Kerdreux, Thomas},
      title = {Efficient Online-bandit Strategies for Minimax Learning Problems}
    }

Conference proceedings

  1. MartĂ­nez-Rubio, D., Roux, C., and Pokutta, S. (2024). Convergence and Trade-offs in Riemannian Gradient Descent and Riemannian Proximal Point. Proceedings of the International Conference on Machine Learning. [URL] [arXiv]
    [BibTeX]
    @inproceedings{2024_MartinezrubioRouxPokutta_Riemanniangradientdescent,
      year = {2024},
      booktitle = {Proceedings of the International Conference on Machine Learning},
      url = {https://proceedings.mlr.press/v235/marti-nez-rubio24a.html},
      archiveprefix = {arXiv},
      eprint = {2403.10429},
      primaryclass = {math.OC},
      author = {MartĂ­nez-Rubio, David and Roux, Christophe and Pokutta, Sebastian},
      title = {Convergence and Trade-offs in Riemannian Gradient Descent and Riemannian Proximal Point}
    }

Full articles

  1. Kerdreux, T., Roux, C., d’Aspremont, A., and Pokutta, S. (2021). Linear Bandits on Uniformly Convex Sets. Journal of Machine Learning Research, 22(284), 1–23. [URL] [arXiv] [summary]
    [BibTeX]
    @article{2021_KerdreuxRouxDaspremontPokutta_Linearbandits,
      year = {2021},
      journal = {Journal of Machine Learning Research},
      month = mar,
      volume = {22},
      number = {284},
      pages = {1–23},
      url = {http://jmlr.org/papers/v22/21-0277.html},
      archiveprefix = {arXiv},
      eprint = {2103.05907},
      primaryclass = {cs.LG},
      author = {Kerdreux, Thomas and Roux, Christophe and d'Aspremont, Alexandre and Pokutta, Sebastian},
      title = {Linear Bandits on Uniformly Convex Sets},
      summary = {https://www.pokutta.com/blog/research/2021/04/03/linearBandits.html}
    }

🔬 Projects

Research Campus MODAL SynLab

SynLab researches mathematical generalization of application-specific advances achieved in the Gas-, Rail– and MedLab of the research campus MODAL. The focus is on exact methods for solving a broad class of discrete-continuous optimization problems. This requires advanced techniques for structure recognition, consideration of nonlinear restrictions from practice, and the efficient implementation of mathematical algorithms on modern computer architectures. The results are bundled in a professional software package and complemented by a range of high-performance methods for specific applications with a high degree of innovation.

SynLab
Apr 2020 to Mar 2025
13
53

đź’¬ Talks and posters

Conference and workshop talks

Nov 2023
Bounding Geometric Penalties in First-order Riemannian Optimization
Seminar "Modern Methods in Applied Stochastics and Nonparametric Statistics"
Mar 2023
Riemannian Optimization: How and Why?
Workshop on Optimization and Machine Learning, Waischenfeld

Research seminar talks

Mar 2025
TBD
IOL Research Seminar (IOL), Berlin
Apr 2024
Bounding Geometric Penalties in Riemannian Optimization
CISPA Research seminar, SaarbrĂĽcken

Poster presentations

Jul 2024
Convergence and Trade-Offs in Riemannian Gradient Descent and Riemannian Proximal Point
41st International Conference on Machine Learning (ICML), Vienna
Mar 2023
Accelerated Riemannian Min-Max Optimization Ensuring Bounded Geometric Penalties
Workshop on Optimization and Machine Learning, Waischenfeld

đź“… Event Attendance