avatar

Nathan Buskulic

Postdoctoral researcher
Machine Learning Center of Genova (MaLGa)
nathan(dot)buskulic(at)proton(dot)me


About Me

Hi! I am a postdoctoral researcher in the Machine Learning center of Genova (MaLGa) working mainly with Luca Calatroni. My work focuses on the theoretical aspects of deep learning when used to solve inverse problems. I am particularly interested in the guarantees that one can achieve with deep learning to help apply this technology to critical domains. I obtained my Ph.D. from Université de Caen in Normandy, France, under the supervision of Jalal Fadili and Yvain Quéau.

News

Selected Publications

Journal articles:

  1. Implicit Regularization of the Deep Inverse Prior Trained with Inertia
    Nathan Buskulic, Jalal Fadili, Yvain Quéau
    Handbook of Numerical Analysis, 2025
    PDF
  2. Convergence and Recovery Guarantees of Unsupervised Neural Networks for Inverse Problems
    Nathan Buskulic, Jalal Fadili, Yvain Quéau
    Journal of Mathematical Imaging and Vision , 2023
    PDF

    3. Conference articles:

  3. Recovery Guarantees of Unsupervised Neural Networks for Inverse Problems trained with Gradient Descent
    Nathan Buskulic, Jalal Fadili, Yvain Quéau
    European Signal Processing Conference, 2024
    PDF Finalist for best paper award
  4. Convergence Guarantees of Overparametrized Wide Deep Inverse Prior
    Nathan Buskulic, Yvain Quéau, Jalal Fadili
    Scale Space and Variational Methods, 2023
    PDF Best paper award
  5. Labelling sulcal graphs across indiviuals using multigraph matching
    Nathan Buskulic, François-Xavier Dupé, Sylvain Takerkart, Guillaume Auzias
    International Symposium on Biomedical Imaging, 2021
    PDF
  6. Maximizing drift is not optimal for solving OneMax
    Nathan Buskulic, Carola Doerr
    Genetic and Evolutionary Computation Conference, 2019
    PDF

Teachings

Université de Caen