by Geonho Hwang Papers
4 papers found
Floating-Point Neural Networks Can Represent Almost All Floating-Point Functions
Geonho Hwang, Yeachan Park, Wonyeol Lee et al.
ICML 2025poster
Minimum Width for Deep, Narrow MLP: A Diffeomorphism Approach
Geonho Hwang
NEURIPS 2025posterarXiv:2308.15873
Minimum Width for Universal Approximation using Squashable Activation Functions
Jonghyun Shin, Namjun Kim, Geonho Hwang et al.
ICML 2025posterarXiv:2504.07371
Optimal Minimum Width for the Universal Approximation of Continuously Differentiable Functions by Deep Narrow MLPs
Geonho Hwang
NEURIPS 2025poster