17 citations · 33 across the 10 of their papers we have counts for
Showing 2023Show all
2 papers · 1 filter
cs.LG2023
Minimum width for universal approximation using ReLU networks on compact domain
Namjun Kim, Chanho Min, Sejun Park
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 character…
cs.LG2023★ 4 cited
Guiding Energy-based Models via Contrastive Latent Variables
Hankook Lee, Jongheon Jeong, Sejun Park +1
An energy-based model (EBM) is a popular generative framework that offers both explicit density and architectural flexibility, but training them is difficult since it is often unst…