I am a PhD student working under the supervision of Jérôme Bolte at Université Toulouse 1 Capitole and Alexandre d'Aspremont within the SIERRA team in Paris.

I currently focus on algorithms for large scale optimization problems, with a special interest for non-Euclidean gradient methods.

More details can be found on my résumé.

Email: radu-alexandru.dragomir [at] inria [dot] fr


  • Optimization
  • Signal processing
  • Machine Learning
  • Non-Euclidean geometries
  • Computer-assisted performance estimation


  • PhD Candidate, since 2018

    Université Toulouse 1 Capitole & D.I. École Normale Supérieure, Paris

  • Master Mathematics, Vision and Learning (MVA), 2018

    ENS Cachan

  • Master's degree in Computer Science and Applied Mathematics, 2017

    École Polytechnique


(2021). Optimal Complexity and Certification of Bregman First-Order Methods. Mathematical Programming.

Code DOI arXiv GeoGebra demo

(2021). Quartic First-Order Methods for Low Rank Minimization. Journal of Optimization Theory and Applications.

Code DOI arXiv