| 2025 | ICLR | The Pitfalls of Memorization: When Memorization Hurts Generalization. | Reza Bayat, Mohammad Pezeshki, Elvis Dohmatob, David Lopez-Paz, Pascal Vincent |
| 2025 | ICLR | Strong Model Collapse. | Elvis Dohmatob, Yunzhen Feng, Arjun Subramonian, Julia Kempe |
| 2025 | ICLR | Beyond Model Collapse: Scaling Up with Synthesized Data Requires Verification. | Yunzhen Feng, Elvis Dohmatob, Pu Yang, Franois Charton, Julia Kempe |
| 2025 | ICLR | An Effective Theory of Bias Amplification. | Arjun Subramonian, Samuel J. Bell, Levent Sagun, Elvis Dohmatob |
| 2025 | ICML | Improving the Scaling Laws of Synthetic Data with Deliberate Practice. | Reyhane Askari Hemmat, Mohammad Pezeshki, Elvis Dohmatob, Florian Bordes, Pietro Astolfi, Melissa Hall, Jakob Verbeek, Michal Drozdzal, Adriana Romero-Soriano |
| 2024 | ICLR | Scaling Laws for Associative Memories. | Vivien Cabannes, Elvis Dohmatob, Alberto Bietti |
| 2024 | ICML | Consistent Adversarially Robust Linear Classification: Non-Parametric Setting. | Elvis Dohmatob |
| 2024 | ICML | A Tale of Tails: Model Collapse as a Change of Scaling Laws. | Elvis Dohmatob, Yunzhen Feng, Pu Yang, Franois Charton, Julia Kempe |
| 2024 | ICML | Precise Accuracy / Robustness Tradeoffs in Regression: Case of General Norms. | Elvis Dohmatob, Meyer Scetbon |
| 2023 | AISTATS | Origins of Low-Dimensional Adversarial Perturbations. | Elvis Dohmatob, Chuan Guo, Morgane Goibert |
| 2023 | AISTATS | Robust Linear Regression: Gradient-descent, Early-stopping, and Beyond. | Meyer Scetbon, Elvis Dohmatob |
| 2023 | ICLR | Contextual bandits with concave rewards, and an application to fair ranking. | Virginie Do, Elvis Dohmatob, Matteo Pirotta, Alessandro Lazaric, Nicolas Usunier |
| 2022 | ICLR | Scalable Sampling for Nonsymmetric Determinantal Point Processes. | Insu Han, Mike Gartrell, Jennifer Gillenwater, Elvis Dohmatob, Amin Karbasi |
| 2022 | ICML | Scalable MCMC Sampling for Nonsymmetric Determinantal Point Processes. | Insu Han, Mike Gartrell, Elvis Dohmatob, Amin Karbasi |
| 2021 | ICLR | Scalable Learning and MAP Inference for Nonsymmetric Determinantal Point Processes. | Mike Gartrell, Insu Han, Elvis Dohmatob, Jennifer Gillenwater, Victor-Emmanuel Brunel |
| 2020 | AAAI | Distributionally Robust Counterfactual Risk Minimization. | Louis Faury, Ugo Tanielian, Elvis Dohmatob, Elena Smirnova, Flavian Vasile |
| 2020 | ICML | Learning disconnected manifolds: a no GAN's land. | Ugo Tanielian, Thibaut Issenhuth, Elvis Dohmatob, Jrmie Mary |
| 2019 | ICML | Generalized No Free Lunch Theorem for Adversarial Robustness. | Elvis Dohmatob |
| 2016 | ICASSP | Local Q-linear convergence and finite-time active set identification of ADMM on a class of penalized regression problems. | Elvis Dohmatob, Michael Eickenberg, Bertrand Thirion, Gal Varoquaux |
| 2015 | MICCAI | Grouping Total Variation and Sparsity: Statistical Learning with Segmenting Penalties. | Michael Eickenberg, Elvis Dohmatob, Bertrand Thirion, Gal Varoquaux |
| 2015 | MICCAI | Integrating Multimodal Priors in Predictive Models for the Functional Characterization of Alzheimer's Disease. | Mehdi Rahim, Bertrand Thirion, Alexandre Abraham, Michael Eickenberg, Elvis Dohmatob, Claude Comtat, Gal Varoquaux |
| 2013 | MICCAI | Extracting Brain Regions from Rest fMRI with Total-Variation Constrained Dictionary Learning. | Alexandre Abraham, Elvis Dohmatob, Bertrand Thirion, Dimitris Samaras, Gal Varoquaux |