About me

I am a research scientist at the RedHat AI Innovation Team and the MIT-IBM Watson AI Lab. I received PhD in Applied Mathematics of the School of Engineering and Applied Sciences (SEAS) at Harvard University. I was fortunate to be advised by Prof. Flavio P. Calmon. My research lies at the intersection of information theory, statistical learning theory, and optimization. My ultimate research goal is to design trustworthy machine learning algorithms with rigorous performance guarantees.

Before joining Harvard University, I received my B.S. degree in Mathematics and Applied Mathematics at the University of Science and Technology of China (USTC) in 2016. I was awarded the 35th Guo Moruo Scholarship which is the highest honor at USTC.

My CV

In memory of Mario Diaz

Publication

  • Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training

    Kristjan Greenewald, Yuancheng Yu, Hao Wang, Kai Xu.
    Advances in Neural Information Processing Systems (NeurIPS), 2024. Paper

  • Quantifying Representation Reliability in Self-Supervised Learning Models

    Young-Jin Park, Hao Wang, Shervin Ardeshir, Navid Azizan.
    Conference on Uncertainty in Artificial Intelligence (UAI), 2024. Paper

  • Post-processing Private Synthetic Data for Improving Utility on Selected Measures

    Hao Wang, Shivchander Sudalairaj, John Henning, Kristjan Greenewald, Akash Srivastava.
    Advances in Neural Information Processing Systems (NeurIPS), 2023. Paper

  • Aleatoric and Epistemic Discrimination: Fundamental Limits of Fairness Interventions

    Hao Wang, Luxi He, Rui Gao, Flavio Calmon.
    Advances in Neural Information Processing Systems (NeurIPS), 2023 (Spotlight). Paper

  • Adapting Fairness Interventions to Missing Values

    Raymond Feng, Flavio Calmon, Hao Wang.
    Advances in Neural Information Processing Systems (NeurIPS), 2023. Paper

  • Analyzing Generalization of Neural Networks through Loss Path Kernels

    Yilan Chen, Wei Huang, Hao Wang, Charlotte Loh, Akash Srivastava, Lam M. Nguyen, Tsui-Wei Weng.
    Advances in Neural Information Processing Systems (NeurIPS), 2023. Paper

  • Information Theory for Trustworthy Machine Learning

    Hao Wang.
    PhD Thesis, Harvard University, 2022. Paper

  • Beyond Adult and COMPAS: Fair Multi-Class Prediction via Information Projection

    Wael Alghamdi, Hsiang Hsu, Haewon Jeong, Hao Wang, Winston Michalak, Shahab Asoodeh, Flavio P. Calmon.
    Advances in Neural Information Processing Systems (NeurIPS), 2022 (Oral Presentation). Paper

  • Generalization Bounds for Noisy Iterative Algorithms Using Properties of Additive Noise Channels

    Hao Wang, Rui Gao, Flavio P. Calmon.
    Journal of Machine Learning Research, 2022. Paper

  • Fairness without Imputation: A Decision Tree Approach for Fair Prediction with Missing Values

    Haewon Jeong, Hao Wang, Flavio P. Calmon.
    AAAI Conference on Artificial Intelligence (AAAI), 2022 (Oral Presentation). Paper

  • Analyzing the Generalization Capability of SGLD Using Properties of Gaussian Channels

    Hao Wang, Yizhe Huang, Rui Gao, Flavio P. Calmon.
    Advances in Neural Information Processing Systems (NeurIPS), 2021. Paper

  • To Split or Not to Split: The Impact of Disparate Treatment in Classification

    Hao Wang, Hsiang Hsu, Mario Diaz, Flavio P. Calmon.
    IEEE Transactions on Information Theory, 2021. Paper

  • The Impact of Split Classifiers on Group Fairness

    Hao Wang, Hsiang Hsu, Mario Diaz, Flavio P. Calmon.
    IEEE International Symposium on Information Theory (ISIT), 2021. Paper

  • Model Projection: Theory and Applications to Fair Machine Learning

    Wael Alghamdi, Shahab Asoodeh, Hao Wang, Flavio P. Calmon, Dennis Wei, Karthikeyan Natesan Ramamurthy.
    IEEE International Symposium on Information Theory (ISIT), 2020. Paper

  • On the Robustness of Information-Theoretic Privacy Measures and Mechanisms

    Mario Diaz*, Hao Wang*, Flavio P. Calmon, Lalitha Sankar. *Equal Contribution
    IEEE Transactions on Information Theory, 2020. Paper

  • An Information-Theoretic View of Generalization via Wasserstein Distance

    Hao Wang, Mario Diaz, José Cândido S. Santos Filho, Flavio P. Calmon.
    IEEE International Symposium on Information Theory (ISIT), 2019. Paper

  • Privacy with Estimation Guarantees

    Hao Wang, Lisa Vo, Flavio P. Calmon, Muriel Médard, Ken R. Duffy, Mayank Varia.
    IEEE Transactions on Information Theory, 2019. Paper

  • Repairing without Retraining: Avoiding Disparate Impact with Counterfactual Distributions

    Hao Wang, Berk Ustun, Flavio P. Calmon.
    International Conference on Machine Learning (ICML), 2019. Paper

  • On the Direction of Discrimination: An Information-Theoretic Analysis of Disparate Impact in Machine Learning

    Hao Wang, Berk Ustun, Flavio P. Calmon.
    IEEE International Symposium on Information Theory (ISIT), 2018. Paper

  • The Utility Cost of Robust Privacy Guarantees

    Hao Wang, Mario Diaz, Flavio P. Calmon, Lalitha Sankar.
    IEEE International Symposium on Information Theory (ISIT), 2018. Paper

  • An Estimation-Theoretic View of Privacy

    Hao Wang, Flavio P. Calmon.
    Annual Allerton Conference on Communication, Control, and Computing, 2017. Paper