Publications
2026
-
Minimax-Optimal Two-Sample Test with Sliced Wasserstein
Binh Thuan Tran, Nicolas Schreuder · AISTATS 2026. PMLR 300:1927-1935
-
A Scalable Nyström-Based Kernel Two-Sample Test with Permutations
Antoine Chatalic, Marco Letizia, Nicolas Schreuder, Lorenzo Rosasco · Electronic Journal of Statistics. DOI:10.1214/26-EJS2537
2025
-
The late-stage training dynamics of (stochastic) subgradient descent on homogeneous neural networks
Sholom Schechtman, Nicolas Schreuder · COLT 2025. PMLR 291:5143-5172
-
Efficient Numerical Integration in Reproducing Kernel Hilbert Spaces via Leverage Scores Sampling
Antoine Chatalic, Nicolas Schreuder, Ernesto De Vito, Lorenzo Rosasco · Journal of Machine Learning Research. 26(101), 1–55 (2025)
2024
-
Addressing bias in online selection with limited budget of comparisons
Ziyad Benomar, Evgenii Chzhen, Nicolas Schreuder, Vianney Perchet · NeurIPS 2024. DOI:10.52202/079017-0361
2023
-
Fair learning with Wasserstein barycenters for non-decomposable performance measures
Solenne Gaucher, Nicolas Schreuder, Evgenii Chzhen · AISTATS 2023. PMLR 206:2436-2459
2022
-
A minimax framework for quantifying risk-fairness trade-off in regression
Evgenii Chzhen, Nicolas Schreuder · Annals of Statistics. 10.1214/22-AOS2198
-
Nyström Kernel Mean Embeddings
Antoine Chatalic, Nicolas Schreuder, Alessandro Rudi, Lorenzo Rosasco · ICML 2022. PMLR 162:3006-3024
2021
-
A study of some trade-offs in statistical learning: online learning, generative models and fairness
Nicolas Schreuder · PhD manuscript. Institut Polytechnique de Paris. tel-03435618
-
Classification with abstention but without disparities
Nicolas Schreuder, Evgenii Chzhen · UAI 2021. Runner-up for best student paper award. PMLR 161:1227-1236
-
Statistical guarantees for generative models without domination
Nicolas Schreuder, Victor-Emmanuel Brunel, Arnak Dalalyan · ALT 2021. PMLR 132:1051-1071
2020
-
An example of prediction which complies with Demographic Parity and equalizes group-wise risks in the context of regression
Evgenii Chzhen, Nicolas Schreuder · NeurIPS 2020 Workshop on Algorithmic Fairness through the Lens of Causality and Interpretability. arXiv:2011.07158
-
Bounding the expectation of the supremum of empirical processes indexed by Hölder classes
Nicolas Schreuder · Math. Meth. Stat. 29, 76–86 (2020). link
-
A nonasymptotic law of iterated logarithm for general M-estimators
Nicolas Schreuder, Victor-Emmanuel Brunel, Arnak Dalalyan · AISTATS 2020. PMLR 108:1331-1341