2023–2026
Research Scientist
Apple Machine Learning Research
Paris, France
Eugene Ndiaye
Research Scientist in Machine Learning and Optimization
I am a researcher in machine learning interested in the reliability of modern statistical models. My work develops mathematical and algorithmic tools that make it possible to attach rigorous guarantees to data-driven predictions, even when models and outputs become more complex. This matters in many settings where predictions inform high-stakes decisions, because it is not enough for a model to produce a single answer; we also need to know when that answer is fragile and how far it can be trusted.
Appointments
2021–2023
Tennenbaum President’s Postdoctoral Fellow
Georgia Institute of Technology
Atlanta, USA
2018–2021
Special Postdoctoral Researcher
RIKEN Center for Advanced Intelligence Project (AIP)
Nagoya, Japan
Education
2015–2018
Télécom Paris, France
Ph.D. in Applied Mathematics
École doctorale de mathématiques Hadamard
Thesis: Safe optimization algorithms for variable selection and hyperparameter tuning.
2012–2015
Université Paris-Saclay, France
Magistère in Fundamental Mathematics and Applications
M.Sc. in Probability and Statistics, with high honors
Selected Publications
Optimization, Sparsity, and Duality
- Gap Safe Screening Rules for Sparsity Enforcing Penalties. E. Ndiaye, O. Fercoq, A. Gramfort, and J. Salmon. Journal of Machine Learning Research, 2017.
- Safe Grid Search with Optimal Complexity. E. Ndiaye, T. Le, O. Fercoq, J. Salmon, and I. Takeuchi. International Conference on Machine Learning, 2019.
- Screening Rules and its Complexity for Active Set Identification. E. Ndiaye, O. Fercoq, and J. Salmon. Journal of Convex Analysis, 2021.
Uncertainty Quantification and Optimal Transport
- Computing Full Conformal Prediction Set with Approximate Homotopy. E. Ndiaye and I. Takeuchi. Advances in Neural Information Processing Systems, 2019.
- Stable Conformal Prediction Sets. E. Ndiaye. International Conference on Machine Learning, 2022. Outstanding Paper Award.
- Root-Finding Approaches for Computing Conformal Prediction Set. E. Ndiaye and I. Takeuchi. Machine Learning, 2023.
- Conformalization of Sparse Generalized Linear Models. E. K. Guha, E. Ndiaye, and X. Huo. International Conference on Machine Learning, 2023.
- Beyond Uncertainty Sets: Leveraging Optimal Transport to Extend Conformal Predictive Distribution to Multivariate Settings. E. Ndiaye. arXiv preprint, 2025.
- Multivariate Conformal Prediction using Optimal Transport. M. Klein, L. Béthune, E. Ndiaye, and M. Cuturi. Transactions on Machine Learning Research, 2026.
- Trained on Tokens, Calibrated on Concepts: The Emergence of Semantic Calibration in LLMs. P. Nakkiran, A. Bradley, A. Goliński, E. Ndiaye, M. Kirchhof, and S. Williamson. International Conference on Learning Representations, 2026.
Complete list on Google Scholar.