Di Wang's Homepage

Chinese: 王帝
PhD candidate
Department of Computer Science and Engineering
State University of New York at Buffalo
Email : dwang45 "at" buffalo.edu

Short Bio

I am a sixth (final) year PhD student in the Department of Computer Science and Engineering at The State University of New York (SUNY) at Buffalo under supervision of Dr. Jinhui Xu . Before that I got my Master degree in Mathematics at University of Western Ontario in 2015, and I got my Bachelor degree in Mathematics and Applied Mathematics at Shandong University in 2014.

My most recent resume (last updated in June, 2020) can be found here.

Dissertation: Some Fundamental Machine Learning Problems in the Differential Privacy Model.

I will be joining the Division of Computer, Electrical and Mathematical Sciences and Engineering (CEMSE), King Abdullah University of Science and Technology (KAUST) as an Assistant Professor. And I will direct the Theoretical, Responsible and trUSTworthy Computing (TRUST) Laboratory.

Current Openings: I am looking for 1 Postdoc, 3-4 PhD students, several internships and visiting students (all are fully funded). If you are interested in working with me, feel free to send me your CV and transcripts.


Research Interests

  • Private Data Analytics: Differential privacy, privacy-preserving machine learning, privacy-preserving data mining, privacy attack in machine learning

  • Trustworthy Machine Learning: Robust statistics/estimation, interpretable machine learning, security in machine learning, adversarial machine learning, fairness in machine learning, other trustworthy issues

  • Statistical Learning Theory: Quantum Machine Learning, Large scale optimization, high dimensional optimization, statistical estimation, learning theory, compressed sensing

  • Machine Learning : Data-driven Machine Learning

  • Healthcare: Trustworthy issues in digital healthcare, biomedical imaging and bioinformatics


  • Professional Experience


    Manuscripts

    1. Statistical Guarantees of Differentially Private (Gradient) Expectation Maximization Algorithm. Abstract
      Di Wang*, Jiahao Ding*, Zejun Xie, Miao Pan and Jinhui Xu (* equal contribution).

    2. Global Interpretation for Pairwise Learning. Abstract
      Mengdi Huai, Di Wang, Jiayi Chen, Jinduo Liu and Aidong Zhang.

    3. Towards Assessment of Randomized Mechanisms for Certifying Adversarial Robustness. Abstract
      Tianhang Zheng*, Di Wang*, Baochun Li and Jinhui Xu (* equal contribution).

    4. Estimating Smooth GLM in Non-interactive Local Differential Privacy Model with Public Unlabeled Data. Abstract
      Di Wang*, Huanyu Zhang*, Marco Gaboardi and Jinhui Xu. (* equal contribution)

    5. Inferring Ground Truth From Crowdsourced Data Under Local Attribute Differential Privacy. Abstract
      Di Wang and Jinhui Xu.


    Selected Publications [Full List] [Google Scholar]

    1. On Sparse Linear Regression in the Local Differential Privacy Model. Abstract
      Di Wang and Jinhui Xu.
      Minor Revision at IEEE Transactions on Information Theory.

    2. Empirical Risk Minimization in the Non-interactive Local Model of Differential Privacy. Abstract
      Di Wang, Marco Gaboardi, Adam Smith and Jinhui Xu.
      Minor Revision at Journal of Machine Learning Research.

    3. On Differentially Private Stochastic Convex Optimization with Heavy-tailed Data. Abstract
      Di Wang*, Hanshen Xiao*, Srini Devadas and Jinhui Xu (* equal contribution).
      The 37th International Conference on Machine Learning (ICML 2020).

    4. Facility Location Problem in Differential Privacy Model Revisited. [Link] Abstract
      [alphabetic order] Yunus Esencayi, Marco Gaboardi, Shi Li and Di Wang
      Conference on Neural Information Processing Systems (NIPS/NeurIPS), 2019.

    5. Differentially Private Empirical Risk Minimization with Non-convex Loss Functions. [Link] Abstract
      Di Wang, Changyou Chen and Jinhui Xu.
      The 36th International Conference on Machine Learning (ICML 2019).

    6. On Sparse Linear Regression in the Local Differential Privacy Model. [Link] Abstract
      Di Wang and Jinhui Xu.
      The 36th International Conference on Machine Learning (ICML 2019).
      Selected as Long Talk(Acceptance Rate: 140/3424= 4.1%) .

    7. Noninteractive Locally Private Learning of Linear Models via Polynomial Approximations. [Link] Abstract
      Di Wang, Adam Smith and Jinhui Xu.
      The 30th International Conference on Algorithmic Learning Theory (ALT 2019).

    8. Empirical Risk Minimization in Non-interactive Local Differential Privacy Revisited. [Link] Abstract
      Di Wang, Marco Gaboardi and Jinhui Xu.
      Conference on Neural Information Processing Systems (NIPS/NeurIPS), 2018.

    9. Differentially Private Empirical Risk Minimization Revisited: Faster and More General. [Link] Abstract
      Di Wang, Minwei Ye and Jinhui Xu.
      Conference on Neural Information Processing Systems (NIPS/NeurIPS), 2017.

    Teaching


    Professional Activities


    Invited Talks


    Awards