Hi! My name is Junhyoung Chung.
I am currently pursuing a master's degree in Statistics at Seoul National University under the supervision of Professor Gunwoong Park. Previously, I obtained my bachelor's degree in Statistics and Economics from the same university.
My academic goal is to develop principled statistical methods that distill essential structures from imperfect and complex data. I aim to bridge the gap between theoretical rigor and practical applicability with the following objectives:
- Developing robust statistical frameworks resilient to data contamination.
- Uncovering latent structures and geometric alignment via optimal transport.
- Establishing theoretical guarantees for reliable machine learning systems.
My research initially focused on probabilistic graphical models, specifically designing consistent structure learning algorithms in the presence of measurement error. Recently, I have expanded my interest to optimal transport, working on Fused Operator Optimal Transport (FOOT) to robustly align non-Euclidean data structures. I have also carried out applied research introducing statistical models tailored to real-world problem solving.
News
- Dec 2025 I will be attending NeurIPS 2025.
- Aug 2025 New paper! "Discovering causal structures in corrupted data: Frugality in anchored Gaussian DAG models" has been published in Computational Statistics and Data Analysis.
- Aug 2025 New paper! "Prediction of high-risk mountain accident areas using a Hurdle model" has been published in Korean Journal of Applied Statistics (written in Korean).