A one-step early stopping rule for underparameterized two-layer networks, with an NTK- and Rademacher-based upper bound on population loss that decreases after one gradient step.
Founda- tions of machine learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
One-Step Early Stopping Strategy using Neural Tangent Kernel Theory and Rademacher Complexity
A one-step early stopping rule for underparameterized two-layer networks, with an NTK- and Rademacher-based upper bound on population loss that decreases after one gradient step.