Omar Chehab

According to our database, Omar Chehab authored at least 8 papers between 2020 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Provable Convergence and Limitations of Geometric Tempering for Langevin Dynamics.

Omar Chehab, Anna Korba, Austin Stromme, Adrien Vacher

CoRR, 2024

A Practical Diffusion Path for Sampling.

Omar Chehab, Anna Korba

CoRR, 2024

2023

Optimizing the Noise in Self-Supervised Learning: from Importance Sampling to Noise-Contrastive Estimation.

Omar Chehab, Alexandre Gramfort, Aapo Hyvärinen

CoRR, 2023

Provable benefits of annealing for estimating normalizing constants: Importance Sampling, Noise-Contrastive Estimation, and beyond.

Omar Chehab, Aapo Hyvärinen, Andrej Risteski

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

2022

The optimal noise in noise-contrastive learning is not what you think.

Omar Chehab, Alexandre Gramfort, Aapo Hyvärinen

Proceedings of the Uncertainty in Artificial Intelligence, 2022

2021

Deep Recurrent Encoder: A scalable end-to-end network to model brain signals.

Omar Chehab, Alexandre Défossez, Jean-Christophe Loiseau, Alexandre Gramfort, Jean-Remi King

CoRR, 2021

Learning with self-supervision on EEG data.

Alexandre Gramfort, Hubert J. Banville, Omar Chehab, Aapo Hyvärinen, Denis A. Engemann

Proceedings of the 9th International Winter Conference on Brain-Computer Interface, 2021

2020

Uncovering the structure of clinical EEG signals with self-supervised learning.

Hubert J. Banville, Omar Chehab, Aapo Hyvärinen, Denis-Alexander Engemann, Alexandre Gramfort

CoRR, 2020