Biography

I am a William T. Tutte Postdoctoral Fellow at the University of Waterloo, hosted by Florian Kerschbaum. Prior to this, I was a Postdoctoral Fellow at the University of Copenhagen, supported by the Providentia project and affiliated with Basic Algorithms Research Copenhagen (BARC), hosted by Rasmus Pagh. I completed my PhD at the University of Melbourne, advised by Anthony Wirth and Olga Ohrimenko.

Research Interests

My research focuses on sketching, graph, and differentially private algorithms, with an emphasis on designing practical solutions backed by rigorous mathematical guarantees. Currently, I am integrating differentially private algorithms with cryptographic security mechanisms to develop secure distributed systems.

Selected Publications

[ICML] Improved Approximations for Hard Graph Problems using Predictions

Anders Aamand, Justin Y. Chen, Siddharth Gollapudi, Sandeep Silwal, Hao Wu (alpha order) 

In International Conference on Machine Learning, 2025

[PODS] Optimal Bounds for Private Minimum Spanning Trees via Input Perturbation

Rasmus Pagh, Lukas Retschmeier, Hao WU, Hanwen Zhang (alpha order) 

In ACM Symposium on Principles of Database Systems, 2025

[ICLR, Spotlight] Learning-Augmented Frequent Directions

Anders Aamand, Justin Y. Chen, Siddharth Gollapudi, Sandeep Silwal, Hao WU (alpha order) 

In International Conference on Learning Representations, 2025

[NeurIPS] Faster Differentially Private Top-k Selection: A Joint Exponential Mechanism with Pruning 

Hao WU, Hanwen Zhang (alpha order)

In Conference on Neural Information Processing Systems, 2024

[ICML] Profile Reconstruction from Private Sketches 

Hao WU, Rasmus Pagh

In International Conference on Machine Learning, 2024

[ICML, Oral] Tight Data Access Bounds for Private Top-k Selection

Hao WU, Olga Ohrimenko, Anthony Wirth 

In International Conference on Machine Learning, Oral, 2023

[PODS] Randomize the Future: Asymptotically Optimal Locally Private Frequency Estimation Protocol for Longitudinal Data  

Olga Ohrimenko, Anthony Wirth, Hao WU (alpha order)

In ACM Symposium on Principles of Database Systems, 2022

[AISTATS] Asymptotically Optimal Locally Private Heavy Hitters via Parameterized Sketches 

Hao WU, Anthony Wirth

In International Conference on Artificial Intelligence and Statistics, 2022

[SIGMOD] Unifying the Global and Local Approaches: An Efficient Power Iteration with Forward Push

Hao WU, Junhao Gan, Zhewei Wei, Rui Zhang 

In International Conference on Management of Data, 2021

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