INSPECTRE: Privately Estimating the Unseen
Jayadev Acharya, Gautam Kamath, Ziteng Sun, Huanyu Zhang, accepted by ICML 2018
CV
Education
- B.S. in Electronics Engineering, Peking University, 2016
- M.S. in Eletrical and Computer Engineering, Cornell University, 2019
- Ph.D in Eletrical and Computer Engineerin, Cornell University, 2021
Work experience
- Research Scientist
- Meta, New York, NY, US
- Summer 2020: Research Scientist Intern
- Facebook, Menlo Park, CA, US
- Differential Privacy, Federated Learning
- Host: Meisam Hejazi Nia
- Summer 2019: Research Intern
- Microsoft Research, Redmond, WA, US
- Differential Privacy, Statistical Machine Learning, NLP
- Host: Janardhan Kulkarni
Publications
Differentially Private Testing of Identity and Closeness of Discrete Distributions
Jayadev Acharya, Ziteng Sun, Huanyu Zhang, accepted by NeurIPS, 2018
Hadamard Response: Estimating Distributions Privately, Efficiently, and with Little Communication
Jayadev Acharya, Ziteng Sun, Huanyu Zhang, accepted by AISTATS 2019
Privately Learning Markov Random Fields
Huanyu Zhang, Gautam Kamath, Janardhan Kulkarni, Zhiwei Steven Wu, accepted by ICML 2020
Locally Private Hypothesis Selection
Sivakanth Gopi, Gautam Kamath, Janardhan Kulkarni, Aleksandar Nikolov, Zhiwei Steven Wu, Huanyu Zhang, accepted by COLT 2020
Estimating Smooth GLM in Non-interactive Local Differential Privacy Model with Public Unlabeled Data
Di Wang, Huanyu Zhang, Marco Gaboardi and Jinhui Xu, accepted by ALT 2021
Differentially Private Assouad, Fano, and Le Cam
Jayadev Acharya, Ziteng Sun, Huanyu Zhang, accepted by ALT 2021
Robust Testing and Estimation under Manipulation Attacks
Jayadev Acharya, Ziteng Sun, Huanyu Zhang, accepted by ICML 2021
Robust Estimation for Random Graphs
Jayadev Acharya, Ayush Jain, Gautam Kamath, Ananda Theertha Suresh, Huanyu Zhang, accepted by COLT 2022
Improved Rates for Differentially Private Stochastic Convex Optimization with Heavy-Tailed Data
Gautam Kamath, Xingtu Liu, Huanyu Zhang, accepted by ICML 2022
Federated Linear Contextual Bandits with User-level Differential Privacy
Ruiquan Huang, Huanyu Zhang, Luca Melis, Milan Shen, Meisam Hejazinia, Jing Yang, accepted by ICML 2023
DP-HyPO: An Adaptive Private Hyperparameter Optimization Framework
Hua Wang, Sheng Gao, Huanyu Zhang, Weijie J Su, Milan Shen, accepted by NeurIPS, 2023
Talks
INSPECTRE: Privately Estimating the Unseen
Oral at ICML 2018, Stockholm, Sweden
Privacy-Preserving Statistical Learning and Testing
Talk at Microsoft Research, Redmond, US
Privately Learning Markov Random Fields
Talk at ICML 2020, virtual
Differentially Private Assouad, Fano, and Le Cam
Talk at ALT 2021, virtual