Omar Chehab

4 papers · 2022–2025 · 4 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12)

Venues

ICLR (1) ICML (1) NeurIPS (1) UAI (1)

Top co-authors

Aapo Hyvärinen (3) Anna Korba (2) Alexandre Gramfort (1) Hanlin Yu (1) Arto Klami (1) Adrien Vacher (1) Andrej Risteski (1) Austin J Stromme (1)

Research topics

Machine Learning (4) Optimization & Theory (3) Mathematics & Optimization (2) Deep Learning (1) Application Areas (1) Bayesian & Probabilistic (1) Learning Types (1) Models (1) Optimization (1) Probability (1)

Keywords

noise contrastive estimation (2) langevin dynamics (1) contrastive learning (1) variational inference (1) self-supervised learning (1) markov chain monte carlo (1) importance sampling (1) partition function (1) density ratio estimation (1) asymptotic variance (1) multimodal distribution (1) generative adversarial network (1) convergence bound (1) normalizing constant (1) error guarantee (1) geometric tempering (1) time scores (1) conditional probability paths (1) generative modeling (1) closed-form objective (1)

Papers

Density Ratio Estimation with Conditional Probability Paths ICML 2025 Provable Convergence and Limitations of Geometric Tempering for Langevin Dynamics ICLR 2025 Provable benefits of annealing for estimating normalizing constants: Importance Sampling, Noise-Contrastive Estimation, and beyond NeurIPS 2023 The optimal noise in noise-contrastive learning is not what you think UAI 2022