Minwoo Kim

I am a postdoctoral researcher working at the Institute for Data Innovation in Science at Seoul National University (서울대학교 과학데이터혁신연구소) since March 2026. I previously worked as a postdoctoral researcher at the Research Institute of Basic Sciences at SNU (2025–2026), and completed my Ph.D. under the supervision of Professor Sungkyu Jung in the Department of Statistics at SNU.

Currently, I am working on some research topics in Statistics including

differentially private multivariate analysis including PCA, correspondence analysis, and discriminant anlaysis,
statistical analysis of data privcy,
high-dimensional multivariate statistical methods,
generalized eigenvalue problems (GEP).

Also, I am interested in nonparametric empircal Bayes estimation, and the role between statistical robustness and data privacy.

Here is my google scholar page.‬

To contact me, email on

ekfgusdl at snu [dot] ac [dot] kr or mwkim.stat at gmail [dot] com

Publications

Minwoo Kim and Sungkyu Jung (2025), "Robust and differentially private principal component analysis," Statistical Analysis and Data Mining, 18(6), e70053. (journal)
Minwoo Kim, Sangil Han, Jeongyoun Ahn and Sungkyu Jung (2025), "Variable selection and basis learning for ordinal classification," Journal of Computational and Graphical Statistics, 34(4), 1432–1445. (journal, arXiv)

Minwoo Kim*, Jonghyeok Lee*, Seung Woo Kwak and Sungkyu Jung (2025), "Differentially Private Multivariate Statistics with an Application to Contingency Table Analysis," Electronic Journal of Statistics, 19(1), 1507-1569. (journal, arXiv) (*: equally contributed)
Sangil Han, Minwoo Kim, Sungkyu Jung and Jeongyoun Ahn (2024), "Sparse ordinal discriminant analysis," Biometrics, 80(1), ujad040. (journal)

Preprints and work in progress

Minwoo Kim, Junyong Park and Sungkyu Jung. "Enhanced Differentially Private Mechanisms via Empirical Bayes," submitted.

Minwoo Kim and Sungkyu Jung. “Non-asymptotic error bound for sparse low-rank structured GEP,” manuscript.

Talks

(Upcoming) "Enhanced differentially private mechanisms via empirical Bayes," IMS Asia Pacific Rim Meeting, Young Researcher's Session, June, 2026, Hong Kong.
(Upcoming) "Robust and differentially private principal component analysis," Theory and Practice of Differential Privacy 2026 (TPDP 2026), Poster Session, June 2026, Boston.
“Sparse ordinal basis learning,” Japanese Joint Statistical Meeting, JSS-KSS-CIPS Joint Session for Young Researchers, September, 2025, Kansai Univ., Osaka, Japan.
“Robust and efficient differentially private PCA for non-Gaussian data,” Korean Statistical Society Winter Conference, 2024, KAIST, Daejeon, Korea.
“Flexible variable selection and basis learning for ordinal classification,” Korean Statistical Society Summer Conference, 2022.06, SNU, Seoul, Korea.

Google Sites

Report abuse