I am a last-year Ph.D. student at Inria, in the Mind team (formerly Parietal). I work with Aapo Hyvärinen and Alexandre Gramfort on statistical estimation of energy-based models.

I hold a master’s degree in applied mathematics and engineering from ENSTA Paris, and a master’s degree in machine learning from ENS Paris-Saclay.

You can reach me at l-emir-omar.chehab [AT] inria.fr


Self-Supervised Learning and Statistical Estimation

Provable benefits of annealing for estimating normalizing constants
O. Chehab, A. Hyvärinen, A. Risteski

Optimizing the Noise: from Importance Sampling to Noise-Contrastive Estimation
O. Chehab, A. Gramfort, A. Hyvärinen

The Optimal Noise in Noise-Contrastive Learning Is Not What You Think
O. Chehab, A. Gramfort, A. Hyvärinen
Uncertainty in Artificial Intelligence (UAI), 2022

Deep Learning and Cognitive Neuroscience

Deep Recurrent Encoder: A scalable end-to-end network to model brain signals
O. Chehab*, A. Defossez*, J.C. Loiseau, A. Gramfort, J.R. King
Journal of Neurons, Behavior, Data analysis, and Theory, 2022

Uncovering the structure of clinical EEG signals with self-supervised learning
H. Banville, O. Chehab, A. Hyvärinen, D. Engemann, A. Gramfort
Journal of Neural Engineering, 2021

A mean-field approach to the dynamics of networks of complex neurons, \n from nonlinear Integrate-and-Fire to Hodgkin-Huxley models
M. Carlu*, O. Chehab*, L. Dalla Porta*, D. Depannemaecker*, C. Héricé*, M. Jedynak*, E. Köksal Ersöz*, P. Muratore*, S. Souihel*, C. Capone, Y. Zerlaut, A. Destexhe, M. di Volo
Journal of Neurophysiology, 2020