3 papers
math.ST2026
Minimax Wasserstein Testing under Differential Privacy
Bonwoo Lee, Ilmun Kim, Cheolwoo Park
We study Wasserstein- goodness-of-fit and two-sample testing under differential privacy. For general compact metric spaces, we establish upper and lower bounds on the minimax se…
stat.ME2025
Geometry-preserving and interpretable dimension reduction for compositional data
Junyoung Park, Cheolwoo Park, Jeongyoun Ahn
High-dimensional compositional data pose unique statistical challenges due to the simplex constraint and excess zeros. While dimension reduction is indispensable for analyzing such…
stat.ML2025
Optimal differentially private kernel learning with random projection
Bonwoo Lee, Cheolwoo Park, Jeongyoun Ahn
Differential privacy has become a cornerstone in the development of privacy-preserving learning algorithms. This work addresses optimizing differentially private kernel learning wi…