A method that alternates gradient steps on a neural network backbone with closed-form optimal updates to the final linear layer under squared loss, including an SGD adaptation and NTK-regime convergence analysis.
[BBSS22] Alberto Bietti, Joan Bruna, Clayton Sanford, and Min Jae Song
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2025 2verdicts
UNVERDICTED 2representative citing papers
The paper derives sharp matching convergence rates for spectral methods in linear regression via feature space decomposition, enabling pre-ordering of algorithms and generalizing saturation effects.
citing papers explorer
-
Closed-Form Last Layer Optimization
A method that alternates gradient steps on a neural network backbone with closed-form optimal updates to the final linear layer under squared loss, including an SGD adaptation and NTK-regime convergence analysis.