Robust/Differentially Private Machine LearningApply
The topic is flexible and depends on student's background, mathematical knowledge, previous research experience. Generally, this project mainly focuses on how to design robust (especially robust against to outliers or heavy-tailed distributions) or private (or forgettable) algorithms for some foundamental problems in machine learning, deep learning or statistics. Students will provide theoretical guarantees via using mathematical tools from probability, learning theory, optimization and high dimensional statistics. Also, student will analyze utility-privacy tradeoff or robustness-utility tradeoff.
Program - Applied Mathematics and Computer Science
Division - Computer, Electrical and Mathematical Sciences and Engineering
Faculty Lab Link - https://shao3wangdi.github.io/
Field of Study - Machine Learning, Data Privacy, High Dimensional Statistics
Desired Project Deliverables
Students will learn some fundamental techniques and results in learning theory, high dimensional statistics, optimization and differential privacy. They will also implement machine learning or statistics algorithms via using Matlab or Python. Hopefully they could have publications after the project.