Denny Wu

activity

20182026

most citedHigh-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation

11 citations · 15 across the 21 of their papers we have counts for

collaborators

Showing 2020Show all

2 papers · 1 filter

stat.ML2020

When Does Preconditioning Help or Hurt Generalization?

Shun-ichi Amari, Jimmy Ba, Roger Grosse +5

While second order optimizers such as natural gradient descent (NGD) often speed up optimization, their effect on generalization has been called into question. This work presents a…

stat.ML2020

On the Optimal Weighted $ℓ_{2}$ Regularization in Overparameterized Linear Regression

Denny Wu, Ji Xu

We consider the linear model $y = X β_{⋆} + ε$ with $X \in R^{n \times p}$ in the overparameterized regime $p > n$ . We estimate $\ma…

When Does Preconditioning Help or Hurt Generalization?

On the Optimal Weighted ℓ2​ Regularization in Overparameterized Linear Regression

On the Optimal Weighted $ℓ_{2}$ Regularization in Overparameterized Linear Regression