3 papers
cs.LG2026
Mitigating the Curse of Dimensionality in Uniform Convergence of Deep Neural Networks via Smooth Activations
Yizhe Ding, Runze Li, Jia Liu +1
This paper establishes a theoretical framework for the uniform convergence of smoothly activated deep neural network (DNN) estimators. While standard ReLU networks achieve minimax-…
math.ST2024
Statistical Convergence Rates of Optimal Transport Map Estimation between General Distributions
Yizhe Ding, Runze Li, Lingzhou Xue
This paper studies the convergence rates of optimal transport (OT) map estimators, a topic of growing interest in statistics, machine learning, and various scientific fields. Despi…
stat.ME2024
Hypothesis Testing for High-Dimensional Matrix-Valued Data
Shijie Cui, Danning Li, Runze Li +1
This paper addresses hypothesis testing for the mean of matrix-valued data in high-dimensional settings. We investigate the minimum discrepancy test, originally proposed by Cragg (…