2 papers
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…
math.FA2024
Conjugating by singular operators: On the boundedness of similarity transforms near singular points
Daniel Falkowski, Carl-Fredrik Lidgren
We consider the question of, given operators , and a sequence of invertible operators , whether the sequence is bounded in norm, as well as generali…