Two steps of gradient descent on first-layer weights in linear-width two-layer networks produce a spiked random matrix with floor(alpha2/(1/2-alpha1)) outliers, each a learned direction, and batch reuse allows capturing directions with information exponent exceeding one.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
A Neyman-orthogonal estimator paired with Lasso nuisance estimation achieves root-T asymptotic normality for BLP demand parameters under high-dimensional controls and approximate sparsity.
citing papers explorer
-
Feature Learning in Linear-Width Two-Layer Networks: Two vs. One Step of Gradient Descent
Two steps of gradient descent on first-layer weights in linear-width two-layer networks produce a spiked random matrix with floor(alpha2/(1/2-alpha1)) outliers, each a learned direction, and batch reuse allows capturing directions with information exponent exceeding one.
-
Estimation of BLP models with high-dimensional controls
A Neyman-orthogonal estimator paired with Lasso nuisance estimation achieves root-T asymptotic normality for BLP demand parameters under high-dimensional controls and approximate sparsity.