Catalog Description: Introduction to fundamental geometric and statistical concepts and principles of low-dimensional models for high-dimensional signal and data analysis, spanning basic theory, efficient algorithms, and diverse real-world applications. Systematic study of both sampling complexity and computational complexity for sparse, low-rank, and low-dimensional models – including important cases such as matrix completion, robust principal component analysis, dictionary learning, and deep networks.

Units: 4

Prerequisites: The following courses are recommended undergraduate linear algebra (Math 110), statistics (Stat 134), and probability (EE126). Back-ground in signal processing (ELENG 123), optimization (ELENG C227T), machine learning (CS189/289), and computer vision (COMPSCI C280) may allow you to appreciate better certain aspects of the course material, but not necessary all at once. The course is open to senior undergraduates, with consent from the instructor.

Fall: 3.0 hours of lecture and 1.0 hours of discussion per week

Grading basis: letter

Final exam status: Written final exam conducted during the scheduled final exam period

Class homepage on inst.eecs