Biography

I am a William T. Tutte Postdoctoral Fellow at the University of Waterloo, hosted by Florian Kerschbaum. Prior to this, I was a postdoc at the University of Copenhagen, hosted by Rasmus Pagh. I completed my PhD at the University of Melbourne, advised by Anthony Wirth and Olga Ohrimenko.

Research Interests

Differential Privacy, Randomized Algorithm

Selected Publications

• Hao WU, Hanwen Zhang, "Faster Differentially Private Top-k Selection: A Joint Exponential Mechanism with Pruning", Conference on Neural Information Processing Systems (NeurIPS), 2024

• Hao WU, Rasmus Pagh, "Profile Reconstruction from Private Sketches", International Conference on Machine Learning (ICML), 2024

• Hao WU, Olga Ohrimenko, Anthony Wirth, "Tight Data Access Bounds for Private Top-k Selection", International Conference on Machine Learning (ICML), Oral, 2023

• Olga Ohrimenko, Anthony Wirth, Hao WU, "Randomize the Future: Asymptotically Optimal Locally Private Frequency Estimation Protocol for Longitudinal Data",  ACM Symposium on Principles of Database Systems (PODS), 2022

• Hao WU, Anthony Wirth, "Asymptotically Optimal Locally Private Heavy Hitters via Parameterized Sketches", International Conference on Artificial Intelligence and Statistics (AISTATS), 2022

• Hao WU, Junhao Gan, Zhewei Wei, Rui Zhang, "Unifying the Global and Local Approaches: An Efficient Power Iteration with Forward Push", International Conference on Management of Data (SIGMOD), 2021

More information about publications can be found on my pages on Google Scholar and DBLP.