Scholar
Omar Chehab
Google Scholar ID: P0nFnfAAAAAJ
Carnegie Mellon University
Citations & Impact
Citations
425
H-index
6
i10-index
5
Publications
15
Co-authors
13
list available
Publications
Resume (English only)
Academic Achievements
- Published several papers, including 'Sampling from multi-modal distributions with polynomial query complexity in fixed dimension via reverse diffusion', 'Provable Convergence and Limitations of Geometric Tempering for Langevin Dynamics', 'A Practical Diffusion Path for Sampling', 'Density Ratio Estimation with Conditional Probability Paths', 'Provable benefits of annealing for estimating normalizing constants: Importance Sampling, Noise-Contrastive Estimation, and beyond', 'The Optimal Noise in Noise-Contrastive Learning Is Not What You Think', 'Multi-View Causal Discovery without Non-Gaussianity: Identifiability and Algorithms', 'MVICAD2: Multi-View Independent Component Analysis with Delays and Dilations'.
Research Experience
- Joined the Machine Learning Department at Carnegie Mellon University as a Postdoctoral Research Associate in Pradeep Ravikumar's team in June 2025; previously worked in the Statistics Department of CREST-ENSAE with Anna Korba's team.
Education
- Completed a PhD in mathematical computer science at Inria in November 2023, advised by Aapo Hyvärinen and Alexandre Gramfort; obtained a Master’s in engineering from ENSTA Paris and in Applied Maths, Vision and Learning (MVA) from ENS Paris-Saclay.
Background
- Research interests include machine learning, particularly on efficient algorithms for estimating and sampling from (energy-based) statistical models, as well as on learning representations of brain activity.
Miscellany
- Contact information includes Email, GitHub, Google Scholar, and LinkedIn.
