Guillaume Lauga
Scholar

Guillaume Lauga

Google Scholar ID: kp4hEB0AAAAJ
Université Côte d'Azur
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
27
 
H-index
3
 
i10-index
1
 
Publications
9
 
Co-authors
0
 
Contact
Emailguillaume.lauga@univ-cotedazur.frCVOpen ↗GitHubOpen ↗
Publications
3 items
Proximal basin hopping: global optimization with guarantees
2026
Cited
0
A block-coordinate descent framework for non-convex composite optimization. Application to sparse precision matrix estimation
2026
Cited
0
A multilevel approach to accelerate the training of Transformers
2025
Cited
0
Resume
Academic Achievements
  • Publications:
  • - IML FISTA: A Multilevel Framework for Inexact and Inertial Forward-Backward. Application to Image Restoration (SIAM Journal on Imaging Sciences, 2024)
  • - A multilevel framework for accelerating uSARA in radio-interferometric imaging (EUSIPCO, 2024, Poster)
Research Experience
  • Was a member of the Inria OCKHAM team; during his PhD, he focused on multilevel optimization methods and their application to image restoration problems.
Education
  • PhD, defended in December 2024 at ENS Lyon, supervised by Paulo Gonçalves, Elisa Riccietti, and Nelly Pustelnik.
Background
  • Research interests: Optimization for imaging applications. Since the start of my PhD, I have been investigating the convergence of proximal algorithms tailored for large-scale problems.
Miscellany
  • Provides Python code implementing IML FB, IML FISTA, and IML PNP algorithms, compatible with the DeepInverse package.