Équipe de recherche :Research Team:
Signal, Statistique et Apprentissage (S2A)Signal, Statistics and Learning (S2A)
Laboratoire :Laboratory:
Laboratoire Traitement et Communication de l'Information (LTCI)Information Processing and Communication Laboratory (LTCI)
Département :Department:
Image, Données, Signal (IDS)Image, Data, Signal (IDS)
Radu Dragomir is an assistant professor in Applied Mathematics in the S2A team at Télécom Paris. His research revolves around numerical optimization methods and interacting particle systems.
He is a chair holder from the Hi! Paris multidisciplinary research center.
Prior to that, he held two post-doctoral positions, at UCLouvain with Yurii Nesterov and then at EPFL Lausanne in the OPTIM group of Nicolas Boumal From 2018 to 2021, he did his PhD jointly with Jérôme Bolte and Alexandre d’Aspremont within the SIERRA team in Paris.
Research activities
He studies optimization methods for solving large-scale problems arising in signal processing and data science. His topics of interest are:
- Particle swarm optimization
- Non-convex optimization
- Gradient descent and its non-Euclidean variants (mirror descent…)
- Dynamics of neural network training
He is also interested on the ethical aspects of machine learning and artificial intelligence. He explores topics such as:
- Reliability of machine learning algorithms
- Political impact of social networks and recommender systems
Teaching activities
- Convex analysis and numerical optimization (Télécom Paris, Master 2 Data Science)
- Optimization for Machine Learning (Télécom Paris, M1)
- Signal processing tools for audio and image (Télécom Paris, L3)
- Numerical analysis (Télécom Paris, M1)
- Ecological and social transition (Télécom Paris, L3)