Failed to load scholar profile
Browse publications on Google Scholar (top-right) ↗
Resume (English only)
Academic Achievements
- Neural Collapse Meets Differential Privacy: Curious Behaviors of NoisyGD with Near-perfect Representation Learning, ICML 2024 (Oral Presentation)
- Threshold KNN-Shapley: A Linear-Time and Privacy-Friendly Approach to Data Valuation, NeurIPS 2023 (Spotlight Presentation)
- Private Prediction Strikes Back! Private Kernelized Nearest Neighbors with Individual Renyi Filter, UAI 2023 (Spotlight Presentation)
- Generalized PTR: User-Friendly Recipes for Data-Adaptive Algorithms with Differential Privacy, AISTATS 2023 (Oral Presentation)
- Women in Machine Learning Workshop (WIML-NeurIPS-2022)
- Optimal Accounting of Differential Privacy via Characteristic Function, AISTATS 2022
- CSS Theory and Practice of Differential Privacy Workshop (TPDP-2021)
- Adaptive Private-K-Selection with Adaptive K and Application to Multi-label PATE, AISTATS 2022
- Voting-based Approaches For Differentially Private Federated Learning, International Workshop on Federated Learning (FL-NeurIPS-2022)
- Improving Sparse Vector Technique with Renyi Differential Privacy, NeurIPS 2020
- CSS Theory and Practice of Differential Privacy Workshop (TPDP-2020)
- Revisiting Model-Agnostic Private Learning: Faster Rates and Active Learning, Journal of Machine Learning Research (JMLR-2022), shorter version appeared in AISTATS 2021
- Model-Agnostic Private Learning with Domain Adaptation, CSS Theory and Practice of Differential Privacy Workshop (TPDP-2020)
- Private-kNN: Practical Differential Privacy for Computer Vision, CVPR 2020
- Poisson Subsampled Rényi Differential Privacy, ICML 2019
Research Experience
- Research Scientist at TikTok
Education
- Ph.D. in Computer Science from UC Santa Barbara, advised by Prof. Yu-Xiang Wang; B.S. in Computer Science from Nanjing University, advised by Prof. Wu-Jun LI
Background
- Research Interests: Machine learning, including differential privacy, domain adaptation, and federated learning. Recently focusing on establishing rigorous differential privacy guarantees for large-scale real datasets. Also working on an open-source project, Auto DP, which aims to help researchers obtain provable DP guarantees with advanced techniques in differential privacy.
Miscellany
- Contact: yuqingzhu0412@gmail.com
- Conference Service: Reviewer for ICML-19, UAI-19, NeurIPS-19, ICML-20, AISTATS-20, ICLR-20, NeurIPS-21, NeurIPS-22, ICML-22, ICML-23
Co-authors: 0 (list not available)