William Fang
MS Student
Computer Science, Mathematics
Boston University
email: wfang "at" bu "dot" edu
About Me
I am interested in private data analysis (differential privacy, unlearning, and synthetic data generation).
I am advised by Mark Bun in the Theoretical Computer Science research group.
Research
Privacy Preserving Machine Learning| Differential Privacy, Learning Theory
-
Privately Learning Decision lists and Differentially Private Winnow
Mark Bun, William Fang
ALT 2026: 37th International Conference on Algorithmic Learning Theory
TPDP 2025: Theory and Practice of Differential Privacy
Privacy Preserving Query Release| Differential Privacy, Learning Theory
-
Design private query release algorithms and lower bounds for nonconvex structures.
Privacy Preserving Synthetic Data Generation| Differential Privacy, Large Language Models
-
Algorithm design of DP-SDA (offline, streaming settings) for LLMs.
Responsible & Safe AI | Machine Unlearning, Computer Vision, XAI
-
Developed a dual-objective approximate machine unlearning algorithm for Image classification (NeurIPS 2023 Machine Unlearning Challenge).
-
Experimented with other unlearning methods (i.e. SCalable Remembering and Unlearning unBound (SCRUB), teacher-student, negative gradient descent, and variants with relative entropy regularization) on CIFAR-10.
-
Graphical Models (on pause)
Service
- Founder, BU ACM-ICPC Team (2020)
- Co-President, SIAM BU Student Chapter
- organizes graduate student and faculty talks on ML, Dynamics, Graphs at the BU SIAM seminar series