Showing 2026Show all
3 papers · 1 filter
stat.ML2026
Increasing Missingness to Reduce Bias: Richardson-SGD with Missing Data
Ferdinand Genans, Erwan Scornet
Stochastic gradient methods are central to modern large-scale learning, but their use with incomplete covariates remains delicate since imputation schemes generally introduce syste…
math.OC2026
Fast and Large-Scale Unbalanced Optimal Transport via its Semi-Dual and Adaptive Gradient Methods
Ferdinand Genans
Unbalanced Optimal Transport (UOT) has emerged as a robust relaxation of standard Optimal Transport, particularly effective for handling outliers and mass variations. However, scal…
stat.ML2026
Geometry-Aware Optimal Transport: Fast Intrinsic Dimension and Wasserstein Distance Estimation
Ferdinand Genans, Olivier Wintenberger
Solving large scale Optimal Transport (OT) in machine learning typically relies on sampling measures to obtain a tractable discrete problem. While the discrete solver's accuracy is…