Ard Louis

collaborators

2 papers

cs.LG2026

Closed-form $ℓ_{r}$ norm scaling with data for overparameterized linear regression and diagonal linear networks under $ℓ_{p}$ bias

Shuofeng Zhang, Ard Louis

For overparameterized linear regression with isotropic Gaussian design and minimum- $ℓ_{p}$ interpolator $p \in (1, 2]$ , we give a unified, high-probability characterization for the s…

cs.LG2026

Position: Many generalization measures for deep learning are fragile

Shuofeng Zhang, Ard Louis

In this position paper, we argue that many post-mortem generalization measures -- those computed on trained networks -- are \textbf{fragile}: small training modifications that bare…

Closed-form ℓr​ norm scaling with data for overparameterized linear regression and diagonal linear networks under ℓp​ bias

Position: Many generalization measures for deep learning are fragile

Closed-form $ℓ_{r}$ norm scaling with data for overparameterized linear regression and diagonal linear networks under $ℓ_{p}$ bias