profile

Postdoctoral Researcher

ENSAE Paris


About

I am a postdoctoral researcher in the Statistics Department of ENSAE Paris and CREST, working with Anna Korba.

I received my PhD in Mathematical Computer Science at Inria, where I was advised by Aapo Hyvärinen and Alexandre Gramfort. I also hold a Master’s in Applied Mathematics and Engineering from ENSTA Paris and another in Mathematics, Vision and Learning (MVA) from Ecole Normale Superieure Paris-Saclay.

My research is in machine learning, particularly on efficient algorithms for estimating and sampling from probabilistic models, as well as on learning useful representations of brain activity.

You can reach me at emir.chehab [AT] ensae.fr


Publications

Sampling from Energy-Based Probabilistic Models

Provable Convergence and Limitations of Geometric Tempering for Langevin Dynamics
O. Chehab, A. Korba, A. Stromme, A. Vacher
Submitted, 2024. Presented at the Workshop "Recent Advances and Future Directions for Sampling" at Yale University.
PAPER   POSTER  
A Practical Diffusion Path for Sampling
O. Chehab, A. Korba
SPIGM Workshop, International Conference on Machine Learning, 2024.
PAPER   POSTER  

Estimating Energy-Based Probabilistic Models

Provable benefits of annealing for estimating normalizing constants: Importance Sampling, Noise-Contrastive Estimation, and beyond
O. Chehab, A. Hyvärinen, A. Risteski
Neural Information Processing Systems, 2023. Spotlight.
PAPER   POSTER   CODE  
Optimizing the Noise in Self-Supervised Learning: from Importance Sampling to Noise-Contrastive Estimation
O. Chehab, A. Gramfort, A. Hyvärinen
Submitted, 2023.
PAPER   CODE  
The Optimal Noise in Noise-Contrastive Learning Is Not What You Think
O. Chehab, A. Gramfort, A. Hyvärinen
Uncertainty in Artificial Intelligence, 2022.
PAPER   POSTER   CODE  

Learning Representations of Brain Activity

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.
PAPER  
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.
PAPER  
Learning with self-supervision on EEG data
A. Gramfort, H. Banville, O. Chehab, A. Hyvärinen, D. Engemann
International Winter Workshop on Brain-Computer Interface, 2021.
PAPER  
A mean-field approach to the dynamics of networks of complex neurons, from nonlinear Integrate-and-Fire to Hodgkin-Huxley models
M. Carlu*, O. Chehab*, [...], A. Destexhe, M. di Volo
Journal of Neurophysiology, 2020.
PAPER  


Talks


Teaching

I was Teacher’s Assistant for the following Masters courses.

Optimization for Data Science - Institut Polytechnique de Paris (2021-2023)
Professors: Alexandre Gramfort, Pierre Ablin
Advanced Machine Learning - CentraleSupelec, Universite Paris-Saclay (2020-2022)
Professors: Emilie Chouzenoux, Frederic Pascal
Optimization - CentraleSupelec, Universite Paris-Saclay (2020-2021)
Professors: Jean-Christophe Pesquet, Sorin Olaru, Stephane Font