13 citations · 29 across the 6 of their papers we have counts for
8 papers
Localized Estimation of Condition Numbers for MILU Preconditioners on a Graph
Geonho Hwang, Yesom Park, Yueun Lee +2
This paper proposes a theoretical framework for analyzing Modified Incomplete LU (MILU) preconditioners. Considering a generalized MILU preconditioner on a weighted undirected grap…
Minimum Width for Deep, Narrow MLP: A Diffeomorphism Approach
Geonho Hwang
Recently, there has been a growing focus on determining the minimum width requirements for achieving the universal approximation property in deep, narrow Multi-Layer Perceptrons (M…
Minimal Width for Universal Property of Deep RNN
Chang hoon Song, Geonho Hwang, Jun ho Lee +1
A recurrent neural network (RNN) is a widely used deep-learning network for dealing with sequential data. Imitating a dynamical system, an infinite-width RNN can approximate any op…
Universal Approximation Property of Fully Convolutional Neural Networks with Zero Padding
Geonho Hwang, Myungjoo Kang
The Convolutional Neural Network (CNN) is one of the most prominent neural network architectures in deep learning. Despite its widespread adoption, our understanding of its univers…
Finding the global semantic representation in GAN through Frechet Mean
Jaewoong Choi, Geonho Hwang, Hyunsoo Cho +1
The ideally disentangled latent space in GAN involves the global representation of latent space with semantic attribute coordinates. In other words, considering that this disentang…
Analyzing the Latent Space of GAN through Local Dimension Estimation
Jaewoong Choi, Geonho Hwang, Hyunsoo Cho +1
The impressive success of style-based GANs (StyleGANs) in high-fidelity image synthesis has motivated research to understand the semantic properties of their latent spaces. In this…
Do Not Escape From the Manifold: Discovering the Local Coordinates on the Latent Space of GANs
Jaewoong Choi, Junho Lee, Changyeon Yoon +3
The discovery of the disentanglement properties of the latent space in GANs motivated a lot of research to find the semantically meaningful directions on it. In this paper, we sugg…
Discond-VAE: Disentangling Continuous Factors from the Discrete
Jaewoong Choi, Geonho Hwang, Myungjoo Kang
In the real-world data, there are common variations shared by all classes (e.g. category label) and exclusive variations of each class. We propose a variant of VAE capable of disen…