Welcome
I am an associate professor (“maître de conférences” in french) in optimization and machine learning at the mathematical institute of the university of Bordeaux (IMB).
From 2022 to 2024, I was a postdoc at the University of Tübingen, working on the TRINOM-DS project led by Peter Ochs and Jalal Fadili. Prior to that, I wrote my PhD thesis (available here) at the IRIT laboratory in Toulouse (supervised by Cédric Févotte, Edouard Pauwels and Jérôme Bolte). I was a member of the FACTORY project.
My research focuses on optimization algorithms for machine learning (mainly second-order methods with application to deep learning), and learning optimization algorithms.
Research interests
- Continuous optimization (convex & non-convex, non-smooth, stochastic)
- Learning to optimize
- Optimization for deep learning & automatic hyper-parameter tuning
Selected publications
From learning to optimize to learning optimization algorithms (2025)
C. Castera, P. Ochs
To appear at AISTATS 2025
arXiv
Continuous Newton-like methods featuring inertia and variable mass (2024)
C. Castera, H. Attouch, J. Fadili, P. Ochs
SIAM Journal on Optimization (SIOPT)
SIOPT | arXiv
An inertial Newton algorithm for deep learning (2021)
C. Castera, J. Bolte, C. Févotte, E. Pauwels
Journal of Machine Learning Research (JMLR)
JMLR | Hal | Code | Poster
Near-optimal closed-loop method via Lyapunov damping for convex optimization (2023)
S. Maier, C. Castera, P. Ochs
Preprint
arXiv | Code
Teaching (University of Bordeaux)
- Large-scale optimization (Master 2)
- Introduction to deep learning (Master 2)
- Convex optimization (Master 1)
- Image processing (Licence 3)
- Tutoring projects on image processing and machine learning
Contact
[firstname].[lastname]@math.u-bordeaux.fr