activity
20162022
most citedTowards a Theoretical Framework of Out-of-Distribution Generalization

41 citations · 89 across the 8 of their papers we have counts for

collaborators
Showing stat.MLShow all

2 papers · 1 filter

stat.ML2023

Heavy-Tailed Regularization of Weight Matrices in Deep Neural Networks

Xuanzhe Xiao, Zeng Li, Chuanlong Xie +1

Unraveling the reasons behind the remarkable success and exceptional generalization capabilities of deep neural networks presents a formidable challenge. Recent insights from rando…

stat.ML2020★ 6 cited

Provable More Data Hurt in High Dimensional Least Squares Estimator

Zeng Li, Chuanlong Xie, Qinwen Wang

This paper investigates the finite-sample prediction risk of the high-dimensional least squares estimator. We derive the central limit theorem for the prediction risk when both the…