Photo
Short Bio Research Interests News Resume Professional Experience Manuscripts Journal Papers Conference Papers Workshop Papers Teaching Professional Activities Awards

Di Wang

PHD candidate
Department of Computer Science and Engineering
State University of New York at Buffalo

Email : dwang45 "at" buffalo.edu, shao3wangdi "at" berkeley.edu
Google Scholar     LinkedIn

Short Bio

I am a fifth (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.


I am on the academic job market this year.

Research Interests

  • Generally speaking, I am interested in Private Data Analytics and Machine Learning .
  • Specifically, my research contains differential privacy, private machine learning, privacy-preserving data mining and crowdsourcing, robust estimation, large scale/ high dimension optimization, adversarial machine learning, interpretable machine learning.
  • Main type of problems I am working on are (Locally) Differentially Private Empirical Risk Minimization, Robust Estimation and Adversrial Machine Learning.



  • News


    Resume


    Professional Experience


    Manuscripts

    1. Global Interpretation for Pairwise Learning Abstract
      Mengdi Huai, Di Wang, Jiayi Chen, Jinduo Liu and Aidong Zhang.
    2. Learning Halfspaces in Non-interactive Local Differential Privacy Model with Public Unlabeled Data Abstract
      Di Wang*, Huanyu Zhang* and Jinhui Xu (* equal contribution).
    3. Inferring Ground Truth From Crowdcourcing Data Under Local Attribute Differential Privacy Abstract
      Di Wang and Jinhui Xu.
    4. On Differentially Private Stochatsic Optimization with Heavy-tailed Data Abstract
      Di Wang*, Hanshen Xiao*, Srini Devadas and Jinhui Xu (* equal contribution).
    5. A Unified Framework For Randomized Smoothing Based Certificated Robustness Abstract
      Tianhang Zheng*, Di Wang*, Baochun Li and Jinhui Xu (* equal contribution).
    6. 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)
    7. Robust Expectation Maximization Algorithm via Trimmed Hard Thresholding Abstract
      Di Wang*, Xiangyu Guo*, Shi Li and Jinhui Xu (* equal contribution).
    8. Escaping Saddle Points of Empirical Risk Privately and Scalably via DP-Trust Region Method Abstract
      Di Wang and Jinhui Xu.

    Journal Papers

    1. On Sparse Linear Regression in the Local Differential Privacy Model. Abstract
      Di Wang and Jinhui Xu.
      Submitted.
      Short version has appeared in ICML 2019.
    2. Differentially Private High Dimensional Sparse Covariance Matrix Estimation. Abstract
      Di Wang and Jinhui Xu.
      Submitted.
      Short version has appeared in CISS 2019.
    3. Empirical Risk Minimization in the Non-interactive Local Model of Differential Privacy. Abstract
      Di Wang, Marco Gaboardi, Adam Smith and Jinhui Xu.
      Submitted.
      Short versions have appeared NeurIPS 2018 and ALT 2019.
    4. Gradient Complexity and Non-stationary Views of Differentially Private Empirical Risk Minimization Abstract
      Di Wang and Jinhui Xu.
      Submitted.
      Short version has appeared in NIPS 2017 and AAAI 2019.
    5. Principal Component Analysis in the Local Differential Privacy Model. Abstract
      Di Wang and Jinhui Xu.
      Minor Revision at Theoretical Computer Science, 2019.
    6. Tight Lower Bound of Locally Differentially Private Sparse Covariance Matrix Estimation Abstract
      Di Wang and Jinhui Xu.
      Minor Revision at Theoretical Computer Science, 2019.
    7. Faster Large Scale Constrained Linear Regression via Two-Step Preconditioning Abstract
      Di Wang and Jinhui Xu.
      Neurocomputing, 364, 280-296.

    Conference Papers

    1. Scalable Estimating Stochastic Linear Combination of Non-linear Regressions. Abstract
      Di Wang* , Xiangyu Guo* , Chaowen Guan, Shi Li and Jinhui Xu (* equal contribution).
      Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020).
    2. Pairwise Learning with Differential Privacy Guarantees. Abstract
      Mengdi Huai*, Di Wang*, Chenglin Miao, Jinhui Xu and Aidong Zhang (* equal contribution).
      Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020).
    3. Towards Interpretation of Pairwise Learning. Abstract
      Mengdi Huai, Di Wang, Chenglin Miao and Aidong Zhang.
      Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI 2020).
    4. Facility Location Problem in Differential Privacy Model Revisited. Abstract
      [alphabetic order] Yunus Esencayi, Marco Gaboardi, Shi Li and Di Wang
      Conference on Neural Information Processing Systems (NIPS/NeurIPS), 2019.
    5. Lower Bound of Locally Differentially Private Sparse Covariance Matrix Estimation. Abstract
      Di Wang and Jinhui Xu.
      28th International Joint Conference on Artificial Intelligence (IJCAI 2019).
    6. Principal Component Analysis in the Local Differential Privacy Model. Abstract
      Di Wang and Jinhui Xu .
      28th International Joint Conference on Artificial Intelligence (IJCAI 2019).
    7. Privacy-aware Synthesizing for Crowdsourced Data. Abstract
      Mengdi Huai, Di Wang, Chenglin Miao, Jinhui Xu, Aidong Zhang.
      28th International Joint Conference on Artificial Intelligence (IJCAI 2019).
    8. Differentially Private Empirical Risk Minimization with Non-convex Loss Functions. Abstract
      Di Wang, Changyou Chen and Jinhui Xu.
      36th International Conference on Machine Learning (ICML 2019).
    9. On Sparse Linear Regression in the Local Differential Privacy Model. Abstract
      Di Wang and Jinhui Xu.
      36th International Conference on Machine Learning (ICML 2019).
      Selected as Long Talk(Acceptance Rate: 140/3424= 4.1%) .
    10. Estimating Sparse Covariance Matrix Under Differential Privacy via Thresholding Abstract
      Di Wang, Jinhui Xu and Yang He.
      53rd Annual Conference on Information Sciences and Systems (CISS 2019).
    11. Noninteractive Locally Private Learning of Linear Models via Polynomial Approximations Abstract
      Di Wang, Adam Smith and Jinhui Xu.
      The 30th International Conference on Algorithmic Learning Theory (ALT 2019).
    12. Differentially Private Empirical Risk Minimization with Smooth Non-convex Loss Functions: A Non-stationary View. Abstract
      Di Wang and Jinhui Xu.
      Thirty-Third AAAI Conference on Artificial Intelligence (AAAI 2019).
      Selected as Oral Presentation (Acceptance Rate: 460/7095=6.5%).
    13. Empirical Risk Minimization in Non-interactive Local Differential Privacy Revisited. Abstract
      Di Wang, Marco Gaboardi and Jinhui Xu.
      Conference on Neural Information Processing Systems (NIPS/NeurIPS), 2018.
    14. Differentially Private Sparse Inverse Covariance Estimation. Abstract
      Di Wang, Mengdi Huai and Jinhui Xu.
      2018 6th IEEE Global Conference on Signal and Information Processing (2018 GlobalSip). Selected as Oral Presentation.
    15. Large Scale Constrained Linear Regression Revisited: Faster Algorithms via Preconditioning. Abstract
      Di Wang and Jinhui Xu.
      Thirty-Second AAAI Conference on Artificial Intelligence (AAAI 2018).
      Selected as Oral Presentation (Acceptance Rate: 411/3800=10.8%).
    16. Differentially Private Empirical Risk Minimization Revisited: Faster and More General. Abstract
      Di Wang, Minwei Ye and Jinhui Xu.
      Conference on Neural Information Processing Systems (NIPS/NeurIPS), 2017.

    Workshop Papers

    1. 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)
      NeurIPS 2019 Workshop on Privacy in Machine Learning.
    2. High Dimensional Sparse Linear Regression under Local Differential Privacy: Power and Limitations Abstract
      Di Wang, Adam Smith and Jinhui Xu .
      NeurIPS 2018 Workshop on Privacy Preserving Machine Learning.

    Teaching


    Professional Activities


    Awards