Publications

Thesis

Supervised learning with missing data: a non-asymptotic point of view (monograph)

Under the supervision of Claire Boyer, Aymeric Dieuleveut and Erwan Scornet

Preprint

Breaking the curse of dimensionality for linear rules: optimal predictors over the ellipsoid (paper) A. Ayme, B.Loureiro Preprint

Accepted papers

Harnessing pattern-by-pattern linear classifiers for prediction with missing data (paper)
A. Reyero Lobo, A. Ayme, C. Boyer, A. Dieuleveut, E. Scornet.
AISTAT 2025

Random features models: a way to study the success of naive imputation (paper)
A. Ayme, C. Boyer, A. Dieuleveut, E. Scornet.
The Forty-first International Conference on Machine Learning (ICML24)

Naive imputation implicitly regularizes high-dimensional linear models (paper)
A. Ayme, C. Boyer, A. Dieuleveut, E. Scornet.
The Fortieth International Conference on Machine Learning (ICML23)

Near optimal rate of consistency for linear models with missing values (paper)
A. Ayme, C. Boyer, A. Dieuleveut, E. Scornet.
The Thirty-ninth International Conference on Machine Learning (ICML22)