Séminaire IMAGE : Radu-Alexandru Dragomir (EPFL), « Optimization methods for large non-quadratic problems »

Nous aurons le plaisir d’accueillir Radu-Alexandru Dragomir , post-doctorant à l’EPFL et candidat au concours CR CNRS 2023 dans l’équipe IMAGE.

Il donnera un séminaire IMAGE, le vendredi 9 décembre à 14h00, en salle F-200.

Résumé :

In this talk, I will give an overview of my research interests. I study optimization problems with highly non-quadratic geometry, such as nonlinear least squares or Poisson deblurring. I particularly focus on the class of quadratic inverse problems arising in low-rank minimization, sensor network localization and phase retrieval. In these problems, the objective functions is a quartic polynomial; a thorough analysis of this structure allows to design well-adapted algorithms, and understand their optimization and statistical properties.