Namjun Kim

2 accepted papers

2025

Minimum Width for Universal Approximation using Squashable Activation Functions

Jonghyun Shin, Namjun Kim, Geonho Hwang, Sejun Park

ICML 2025poster

The exact minimum width that allows for universal approximation of unbounded-depth networks is known only for ReLU and its variants. In this work, we study the minimum width of networks using general activation functions. Specifically, we focus on squashable functions that can approximate the identi…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Minimum width for universal approximation using ReLU networks on compact domain

Namjun Kim, Chanho Min, Sejun Park

ICLR 2024poster

It has been shown that deep neural networks of a large enough width are universal approximators but they are not if the width is too small. There were several attempts to characterize the minimum width $w_{\min}$ enabling the universal approximation property; however, only a few of them found the ex…

Cited by 12 Source ↗PDF ↗Scholar ↗