Skip over navigation

Course Offerings

Course Evaluation Results

Course Details

Fall 2018-2019
ELE 538B   Graded A-F, P/D/F, Audit

Special Topics in Information Sciences and Systems - Mathematics of High-Dimensional Data

Yuxin Chen

This is a graduate level course covering various aspects of mathematical data science, particularly for large-scale problems. We cover the mathematical foundations of several fundamental inference/learning/estimation problems, including sparse representation and recovery, low-rank matrix recovery, robust principal component analysis, spectral methods, methods of moments, graph clustering, etc. Both convex and nonconvex approaches are discussed. We focus on designing algorithms that are effective in both theory and practice.

Sample reading list:
Wainwright, Martin, High-dimensional statistics: A non-asymptotic viewpoint
Fan, Li, Zhang, Zou, Statistical machine learning for high-dimensional data
Wright, Ma, Yang, High-dimensional data analysis with sparse models: Theory, a

Requirements/Grading:
Design Project - 60%
Problem set(s) - 40%

Other Requirements:
Not Open to First Year Undergraduates.

Prerequisites and Restrictions:
Students should have backgrounds in basic linear algebra and in basic probability (measure- theoretic probability is not needed), as well as knowledge of a programming language like MATLAB or Python to conduct simple simulation exercises. While no specific background in optimization is required, a course such as ORF307 (Optimization) would be beneficial..

Website:  http://www.princeton.edu/~yc5/ele538_math_data/index.html

Schedule/Classroom assignment:

Class numberSectionTimeDaysRoomEnrollmentStatus
23440 L01 09:30:00 am - 10:50:00 am M W   Sherrerd Hall   101   Enrolled:37 Limit:50