Victor Léger

Ph.D. – Theoretical guarantees and improvement of large dimensional multi-task semi-supervised classification [manuscript]

Academic Background

• Master MVA   Mathematics, Machine Learning, Computer Vision
• ENS Paris-Saclay   Mathematics Department

Research topics

High-Dimensional Statistics   Random Matrix Theory   Machine learning   Signal Processing

Publications

• Submitted to IEEE Transactions on Signal Processing – A Large Dimensional Analysis of Multi-task Semi-Supervised Learning, Victor Léger, Romain Couillet [preprint][code]
• EUSIPCO 2024 – Asymptotic Bayes risk of semi-supervised learning with uncertain labeling, Victor Léger, Romain Couillet [article]

• GRETSI 2023 – Apprentissage semi-supervisé avec données partiellement étiquetées, Victor Léger, Romain Couillet [article]
• GRETSI 2022 – Classification multi-tâches semi-supervisée en grande dimension, Victor Léger, Malik Tiomoko, Romain Couillet [article]