Publications

Publications

Imputation for prediction: beware of diminishing returns.
Marine Le Morvan, Gaël Varoquaux
In arXiv preprint arXiv:2407.19804 (2024)

BOOM! Tephrochronological dataset and exploration tool of the Southern (33–46° S) and Austral (49–55° S) volcanic zones of the Andes.
Consuelo Martínez Fontaine, Vanessa Peña-Araya, Chiara Marmo, Marine Le Morvan, Guillaume Delpech, Karen Fontijn, Giuseppe Siani, Lucile Cosyn-Wexsteen
In Quaternary Science Reviews (2023) paper

Beyond calibration: estimating the grouping loss of modern neural networks..
Alexandre Perez-Lebel, Marine Le Morvan, Gaël Varoquaux
In International Conference on Learning Representations (ICLR 2022) paper

Benchmarking missing-values approaches for predictive models on health databases.
Alexandre Perez-Lebel, Gaël Varoquaux, Marine Le Morvan, Julie Josse, Jean-Baptiste Poline
In GigaScience (2022) paper

What’s a good imputation to predict with missing values?
Marine Le Morvan, Julie Josse, Erwan Scornet, Gaël Varoquaux
In Advances in Neural Information Processing Systems (Neurips 2021 spotlight) paper code poster

NeuMiss networks: differentiable programming for supervised learning with missing values.
Marine Le Morvan, Julie Josse, Thomas Moreau, Erwan Scornet, Gaël Varoquaux
In Advances in Neural Information Processing Systems (NeurIPS 2020 oral)
paper code poster 3min video

Linear predictor on linearly-generated data with missing values: non consistency and solutions.
Marine Le Morvan, Nicolas Prost, Julie Josse, Erwan Scornet, Gaël Varoquaux
in Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics (AIStats 2020)
paper code

WHInter: A Working set algorithm for High-dimensional sparse second order Interaction models.
Marine Le Morvan, Jean-Philippe Vert
In Proceedings of the 35th International Conference on Machine Learning (ICML 2018)
paper code

Supervised quantile normalisation.
Marine Le Morvan, Jean-Philippe Vert
Preprint, 2017
paper

NetNorM: Capturing cancer-relevant information in somatic exome mutation data with gene networks for cancer stratification and prognosis.
Marine Le Morvan, Andreï Zinovyev, Jean-Philippe Vert
In PLoS computational biology (2017)
paper code

PhD Thesis

Learning from genomic data : efficient representations and algorithms.
Marine Le Morvan
PhD Thesis (2018)
manuscript