skip to main content

Foundations of Private and Fair Statistics

Project

Project Details

Program
Statistics
Field of Study
Machine Learning, Data Privacy, Statistics
Division
Computer, Electrical and Mathematical Sciences and Engineering

Project Description

The topic is flexible and depends on student's background, previous experience and mathematical skill. Specifically, in the topic, students will explore basic statistical model or problems for different types of data in the differential privacy or fairness model. For statistical model , topics include component analysis, supervised learning, mixture model , et al. For data, topics include survival data, functional data, network analysis. Students will design new algorithms to solve these problems and provide theoretical guarantees on the utility-privacy or utility-fairness tradeoff. Moreover, they will implement these algorithms on some sensitive data such as healthcare and biomedical data.

About the Researcher

Di Wang
Assistant Professor, Computer Science
Computer, Electrical and Mathematical Science and Engineering Division

Affiliations

Education Profile

  • 2020 Ph.D State University of New York at Buffalo
  • 2015 M.S. Western University, 2014 B.S. Shandong University

Research Interests

Professor Wang's interests are differential privacy, privacy-preserving machine learning, privacy-preserving data mining, privacy attack in machine learning, trustworthy machine learning, statistical learning theory. He is also interested in trustworthy issues in digital healthcare, biomedical imaging and bioinformatics.a€‹

Selected Publications

  • Di Wang, Hanshen Xiao, Srini Devadas, and Jinhui Xu. ""On Differentially Private Stochatsic Optimization with Heavy-tailed Data"" In International Conference on Machine Learning. 2020.
  • Di Wang, Changyou Chen, and Jinhui Xu. ""Differentially private empirical risk minimization with non-convex loss functions."" In International Conference on Machine Learning, pp. 6526-6535. 2019.
  • Di Wang, and Jinhui Xu. ""On sparse linear regression in the local differential privacy model."" In International Conference on Machine Learning, pp. 6628-6637. 2019.
  • Di Wang, Marco Gaboardi, and Jinhui Xu. ""Empirical risk minimization in non-interactive local differential privacy revisited."" In Advances in Neural Information Processing Systems, pp. 965-974. 2018.
  • Di Wang, Minwei Ye, and Jinhui Xu. ""Differentially private empirical risk minimization revisited: Faster and more general."" In Advances in Neural Information Processing Systems, pp. 2722-2731. 2017.

Desired Project Deliverables

Students will learn basic techniques and terminologies in differential privacy, fairness and some topics in statistics. They will have the chance to implement the best-known algorithm for some specific problems. Hopefully, they could have some new results and publications after the project.

Recommended Student Background

Optimization
Statistics
Probability
Machine Learning