Portrait de Mahdi Ghaznavi

Mahdi Ghaznavi

Superviseur⋅e principal⋅e
Ioannis Mitliagkas
Sujets de recherche
Apprentissage de représentations
Apprentissage profond
Généralisation
Généralisation hors distribution (OOD)
IAG (Intelligence Artificielle Générale)
Modèles de fondation
Optimisation
Google Scholar
GitHub

Publications

The Geometry of Spectral Gradient Descent: Layerwise Criteria for SignSGD vs SpecSGD
Hiroki Naganuma
Laura Gomezjurado
Mahdi Ghaznavi
Ioannis Mitliagkas
Optimization in deep learning has expanded beyond Euclidean methods to include entrywise sign updates (SignSGD) and spectral sign updates (S… (voir plus)pecGD/Muon). While both can be viewed as steepest descent under non-Euclidean geometries (
2026-03-01
GRaM @ International Conference on Learning Representations (poster)
openreview.net
openreview.net