13 citations · 36 across the 14 of their papers we have counts for
15 papers
Robust training and rigorous error analysis of physics-informed neural networks for the -Laplace equation
Kyueon Choi, Seungchan Ko, Dohyun Kwon
With the rise of scientific machine learning, physics-informed neural networks (PINNs) have been extensively applied to a wide range of problems. Nevertheless, most theoretical ana…
Complexity of Block Coordinate Descent with Proximal Regularization and Applications to Wasserstein CP-dictionary Learning
Dohyun Kwon, Hanbaek Lyu
We consider the block coordinate descent methods of Gauss-Seidel type with proximal regularization (BCD-PR), which is a classical method of minimizing general nonconvex objectives…
A Fully First-Order Method for Stochastic Bilevel Optimization
Jeongyeol Kwon, Dohyun Kwon, Stephen Wright +1
We consider stochastic unconstrained bilevel optimization problems when only the first-order gradient oracles are available. While numerous optimization methods have been proposed…
Score-based Generative Modeling Secretly Minimizes the Wasserstein Distance
Dohyun Kwon, Ying Fan, Kangwook Lee
Score-based generative models are shown to achieve remarkable empirical performances in various applications such as image generation and audio synthesis. However, a theoretical un…
The regularity with respect to domains of the additive eigenvalues of superquadratic Hamilton--Jacobi equation
Farid Bozorgnia, Dohyun Kwon, Son N. T. Tu
We study the additive eigenvalues on changing domains, along with the associated vanishing discount problems. We consider the convergence of the vanishing discount problem on chang…
Training Wasserstein GANs without gradient penalties
Dohyun Kwon, Yeoneung Kim, Guido Montúfar +1
We propose a stable method to train Wasserstein generative adversarial networks. In order to enhance stability, we consider two objective functions using the -transform based on…