3 papers
math.PR2026
A functional central limit theorem for kernel gradient flow and infinitesimal gradient boosting
Clément Dombry, Jean-Jil Duchamps
Building on the large-sample analysis of infinitesimal gradient boosting (Dombry and Duchamps, 2024b), we study the fluctuations of the process around its deterministic limit and e…
stat.ML2026
Out-of-Distribution generalization of quantile regression with heavy tailed inputs: an SVM approach
Baptiste Leroux, Clément Dombry, Anne Sabourin
We study quantile regression in an extrapolation regime where the covariate takes unusually large values. Under regular variation assumptions, extreme observations can be effective…
math.ST2025
Distributional regression with reject option
Ahmed Zaoui, Clément Dombry
Selective prediction, where a model has the option to abstain from making a decision, is crucial for machine learning applications in which mistakes are costly. In this work, we fo…