← Search

Hyunouk Ko

2 accepted papers

2024

Universal Consistency of Wide and Deep ReLU Neural Networks and Minimax Optimal Convergence Rates for Kolmogorov-Donoho Optimal Function Classes

ICML 2024poster

In this paper, we prove the universal consistency of wide and deep ReLU neural network classifiers. We also give sufficient conditions for a class of probability measures for which classifiers based on neural networks achieve minimax optimal rates of convergence. The result applies to a wide range o…

Cited by 1SourcePDFScholar
2022

A NON-PARAMETRIC REGRESSION VIEWPOINT : GENERALIZATION OF OVERPARAMETRIZED DEEP RELU NETWORK UNDER NOISY OBSERVATIONS

ICLR 2022poster

We study the generalization properties of the overparameterized deep neural network (DNN) with Rectified Linear Unit (ReLU) activations. Under the non-parametric regression framework, it is assumed that the ground-truth function is from a reproducing kernel Hilbert space (RKHS) induced by a neural t…

Cited by 13SourcePDFScholar