Radu-Alexandru Dragomir
- Researcher in numerical optimization and data science -
About me
Since 2024, I am an assistant professor in Applied Mathematics in the
S2A team at
Télécom Paris. My research revolves around machine learning and signal processing methods.
Prior to that, I held two post-doctoral positions, at UCLouvain with Yurii Nesterov and then at EPFL in the OPTIM group of Nicolas Boumal.
From 2018 to 2021, I did my PhD jointly with Jérôme Bolte and Alexandre d'Aspremont within the SIERRA team in Paris.
Email: dragomir [at] telecom-paris.fr
Research
I study optimization methods for solving large-scale problems arising in signal processing and data science. My research revolves around understanding problems with non-quadratic and non-convex objectives. Among others, I am interested in:
- Mirror descent
- Implicit bias of neural network training
- Nonlinear inverse problems
- Computer-aided performance estimation
I am also interested on the ethical aspects of machine learning and artificial intelligence. I explore topics such as:
- Reliability and robustness of machine learning algorithms
- Political impact of social networks and recommender systems
- Environnmental cost of AI
Teaching
- Optimization for Machine Learning (Télécom Paris, M1)
- Signal processing tools for audio and image (Télécom Paris, L3)
- Numerical analysis (Télécom Paris, L3)
- Ecological and social transition (Télécom Paris, L3)
Preprints
- R-A. Dragomir, Y. Nesterov. Convex Quartic Problems: Homogenized Gradient Method and Preconditioning.
[arxiv]
[slides]
[slides]
Publications
- S. Pesme, R-A. Dragomir, N. Flammarion. Implicit Bias of Mirror Flow on Separable Data.
NeurIPS, 2024.
[arxiv]
- R-A. Dragomir, M. Even, H. Hendrikx. Fast Stochastic Bregman Gradient Methods: Sharp Analysis and Variance Reduction.
International Conference on Machine Learning, 2021.
[PMLR]
[arxiv] [slides]
- R-A. Dragomir, A. B. Taylor, A. d'Aspremont, J. Bolte. Optimal Complexity and Certification of Bregman First-Order Methods.
Mathematical Programming, 2021.
[springer]
[arxiv]
[GeoGebra demo]
[code]
- R-A. Dragomir, A. d'Aspremont, J. Bolte. Quartic First-Order Methods for Low-Rank Minimization.
Journal of Optimization Theory and Applications, 2021.
[springer]
[arxiv]
[code]
Thesis
- R-A. Dragomir, Bregman Gradient Methods for Relatively-Smooth Optimization.
PhD thesis, 2021.
Advised by Jérôme Bolte and Alexandre d'Aspremont. [pdf]
[slides]
[video]