Hello, Friend.
I am a Ph.D. student at Halıcıoğlu Data Science Institute, UC San Diego, where I am fortunate to be advised by Prof. Yu-Xiang Wang and to work closely with Prof. Yi-An Ma.
My research interests lie in differentially private machine learning. Recently, I have being thinking how tecniques from differential privacy can address safety concerns in generative models.
Selected Papers (* denotes equal contribution)
Adapting to Linear Separable Subsets with Large-Margin in Differentially Private Learning
Erchi Wang, Yuqing Zhu, Yu-Xiang Wang
International Conference on Machine Learning (ICML) 2025. Arxiv preprint
Theory and Practice of Differential Privacy workshop (TPDP) 2025, oral presentation.
Privacy-Preserving Machine Learning Workshop (PPML) in Crypto 2025, contributed talk
Purifying Approximate Differential Privacy with Randomized Post-processing
Yingyu Lin* , Erchi Wang*, Yi-An Ma, Yu-Xiang Wang
Arxiv preprint
Theory and Practice of Differential Privacy workshop (TPDP) 2025, oral presentation.
Beyond Per-Question Privacy: Multi-Query Differential Privacy for RAG Systems
Ruihan Wu*, Erchi Wang*, Yu-Xiang Wang
Manuscript
Education
University of California San Diego
Ph.D. in Data Science
Jul 2024 - Now
University of California Santa Barbara
M.A. in Statistics
Sep 2021 - Jun 2024. (Transferred to UCSD)
Contact
erw011@ucsd.edu