Guillaume Lecué

13 catalog papers. Identity-linked publications and additional name matches are distinguished below.

ORCID: 0000-0002-6391-8746

ESSEC, Business School

Publications

• A geometrical analysis of kernel ridge regression and its applications — The Annals of Statistics 2025
• Learning with a linear loss function: excess risk and estimation bounds for ERM, minmax MOM and their regularized versions with applications to robustness in sparse PCA. — Journal of Machine Learning Research 2024 (name-matched, not ORCID-linked)
• Robust sub-Gaussian estimation of a mean vector in nearly linear time — The Annals of Statistics 2022
• Learning with semi-definite programming: statistical bounds based on fixed point analysis and excess risk curvature — Journal of Machine Learning Research 2021 (name-matched, not ORCID-linked)
• Robust machine learning by median-of-means: Theory and practice — The Annals of Statistics 2020
• Estimation bounds and sharp oracle inequalities of regularized procedures with Lipschitz loss functions — The Annals of Statistics 2019
• Regularization and the small-ball method I: Sparse recovery — The Annals of Statistics 2018
• Regularization and the small-ball method II: complexity dependent error rates — Journal of Machine Learning Research 2017 (name-matched, not ORCID-linked)
• Optimal learning with Q-aggregation — The Annals of Statistics 2014 (name-matched, not ORCID-linked)
• General nonexact oracle inequalities for classes with a subexponential envelope — The Annals of Statistics 2012 (name-matched, not ORCID-linked)
• Hyper-Sparse Optimal Aggregation — Journal of Machine Learning Research 2011 (name-matched, not ORCID-linked)
• Simultaneous adaptation to the margin and to complexity in classification — The Annals of Statistics 2007
• Lower Bounds and Aggregation in Density Estimation — Journal of Machine Learning Research 2006 (name-matched, not ORCID-linked)