Early-stopped gradient descent dominates ridge regression for all well-specified linear regression problems, and it dominates stochastic gradient descent whenever the covariance spectrum decays fast and continuously.
Boosting with the L_2 loss: regression and classification
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Risk Comparisons in Linear Regression: Implicit Regularization Dominates Explicit Regularization
Early-stopped gradient descent dominates ridge regression for all well-specified linear regression problems, and it dominates stochastic gradient descent whenever the covariance spectrum decays fast and continuously.