ScoreStop introduces a functional score test for early stopping in gradient boosting, testing the null that the current predictor minimizes population risk with a scale-invariant statistic of known asymptotic distribution.
Boosting With the L2 Loss: Regression and Classification
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
roles
baseline 1polarities
baseline 1representative citing papers
MIBoost extends gradient boosting to multiple imputation by defining a single loss function that produces one set of selected variables across all imputed datasets.
Proves that rescaled deviations of kernel gradient flow and infinitesimal gradient boosting from their deterministic ODE limits converge to a Gaussian process via a general stochastic perturbation analysis of ODEs in Banach spaces.
Large-scale neutral benchmark of survival models on low-dimensional right-censored data finds Cox PH performs comparably to more complex methods across discrimination, calibration, and predictive metrics.
citing papers explorer
-
ScoreStop: Gradient-based early stopping using functional score tests
ScoreStop introduces a functional score test for early stopping in gradient boosting, testing the null that the current predictor minimizes population risk with a scale-invariant statistic of known asymptotic distribution.
-
A functional central limit theorem for kernel gradient flow and infinitesimal gradient boosting
Proves that rescaled deviations of kernel gradient flow and infinitesimal gradient boosting from their deterministic ODE limits converge to a Gaussian process via a general stochastic perturbation analysis of ODEs in Banach spaces.
-
A Large-Scale Neutral Comparison Study of Survival Models on Low-Dimensional Data
Large-scale neutral benchmark of survival models on low-dimensional right-censored data finds Cox PH performs comparably to more complex methods across discrimination, calibration, and predictive metrics.