1 citations · 1 across the 6 of their papers we have counts for
Showing 2026 · stat.MLShow all
2 papers · 2 filters
stat.ML2026
Affine-invariant Cubic Newton with Weak Learners
Nikita Zozoulenko, Daniel Falkowski, Thomas Cass +1
Modern gradient boosting algorithms are based on Newton's method, which excels empirically but lacks global convergence guarantees. While recent work on Gradient-Regularized Newton…
stat.ML2026
Gradient Regularized Newton Boosting Trees with Global Convergence
Nikita Zozoulenko, Daniel Falkowski, Thomas Cass +1
Gradient Boosting Decision Trees (GBDTs) dominate tabular machine learning, with modern implementations like XGBoost, LightGBM, and CatBoost being based on Newton boosting: a secon…