2 papers
stat.ML2024
Universal Consistency of Wide and Deep ReLU Neural Networks and Minimax Optimal Convergence Rates for Kolmogorov-Donoho Optimal Function Classes
Hyunouk Ko, Xiaoming Huo
In this paper, we prove the universal consistency of wide and deep ReLU neural network classifiers trained on the logistic loss. We also give sufficient conditions for a class of p…
stat.ME2019
Sequential and Simultaneous Distance-based Dimension Reduction
Yijin Ni, Chuanping Yu, Andy Ko +1
This paper introduces a method called Sequential and Simultaneous Distance-based Dimension Reduction () that performs simultaneous dimension reduction for a pair of random…