Omar Chehab

17 papers A* 3A 1Journal 12Unranked 1
YearRankTypeTitle / Venue / Authors
2026 J jnl
MVICAD
IEEE Trans. Biomed. Eng.
Ambroise Heurtebise, Omar Chehab, Pierre Ablin, Alexandre Gramfort
2025 A* conf
Density Ratio Estimation with Conditional Probability Paths.
ICML
Hanlin Yu, Arto Klami, Aapo Hyvärinen, Anna Korba, Omar Chehab
2025 J jnl
Density Ratio Estimation with Conditional Probability Paths.
CoRR
Hanlin Yu, Arto Klami, Aapo Hyvärinen, Anna Korba, Omar Chehab
2025 J jnl
Identifiable Multi-View Causal Discovery Without Non-Gaussianity.
CoRR
Ambroise Heurtebise, Omar Chehab, Pierre Ablin, Alexandre Gramfort, Aapo Hyvärinen
2025 J jnl
MVICAD2: Multi-View Independent Component Analysis with Delays and Dilations.
CoRR
Ambroise Heurtebise, Omar Chehab, Pierre Ablin, Alexandre Gramfort
2025 J jnl
Polynomial time sampling from log-smooth distributions in fixed dimension under semi-log-concavity of the forward diffusion with application to strongly dissipative distributions.
CoRR
Adrien Vacher, Omar Chehab, Anna Korba
2025 A* conf
Provable Convergence and Limitations of Geometric Tempering for Langevin Dynamics.
ICLR
Omar Chehab, Anna Korba, Austin J. Stromme, Adrien Vacher
2024 J jnl
A Practical Diffusion Path for Sampling.
CoRR
Omar Chehab, Anna Korba
2024 J jnl
Provable Convergence and Limitations of Geometric Tempering for Langevin Dynamics.
CoRR
Omar Chehab, Anna Korba, Austin J. Stromme, Adrien Vacher
2023 J jnl
Optimizing the Noise in Self-Supervised Learning: from Importance Sampling to Noise-Contrastive Estimation.
CoRR
Omar Chehab, Alexandre Gramfort, Aapo Hyvärinen
2023 A* conf
Provable benefits of annealing for estimating normalizing constants: Importance Sampling, Noise-Contrastive Estimation, and beyond.
NeurIPS
Omar Chehab, Aapo Hyvärinen, Andrej Risteski
2023 J jnl
Provable benefits of annealing for estimating normalizing constants: Importance Sampling, Noise-Contrastive Estimation, and beyond.
CoRR
Omar Chehab, Aapo Hyvärinen, Andrej Risteski
2022 J jnl
The Optimal Noise in Noise-Contrastive Learning Is Not What You Think.
CoRR
Omar Chehab, Alexandre Gramfort, Aapo Hyvärinen
2022 A conf
The optimal noise in noise-contrastive learning is not what you think.
UAI
Omar Chehab, Alexandre Gramfort, Aapo Hyvärinen
2021 J jnl
Deep Recurrent Encoder: A scalable end-to-end network to model brain signals.
CoRR
Omar Chehab, Alexandre Défossez, Jean-Christophe Loiseau, Alexandre Gramfort, Jean-Remi King
2021 — conf
Learning with self-supervision on EEG data.
BCI
Alexandre Gramfort, Hubert J. Banville, Omar Chehab, Aapo Hyvärinen, Denis A. Engemann
2020 J jnl
Uncovering the structure of clinical EEG signals with self-supervised learning.
CoRR
Hubert J. Banville, Omar Chehab, Aapo Hyvärinen, Denis-Alexander Engemann, Alexandre Gramfort