SEEM 5380: Optimization Methods for High-Dimensional Statistics

2016-17 Second Term


General Information

  • Instructor: Anthony Man-Cho So (manchoso at
  • Office Hours: Wednesdays 3:00pm - 4:30pm or by appointment, in ERB 604
  • Lecture Time/Location:
    • Mondays 11:30am - 1:15pm, in LSB C2
    • Tuesdays 11:30am - 1:15pm, in HYS LG04

Course Description

The prevalence of high-dimensional data has motivated active research on efficient methods for tackling optimization problems that arise in statistical analysis. In this course, we will give an introduction to this exciting area of research, with emphasis on the theory of structured regularizers for high-dimensional statistics and the design and analysis of statistically and computationally efficient optimization algorithms. Applications in various areas of science and engineering, such as machine learning, signal processing, and statistics, will also be discussed. Prerequisite: ENGG 5501 or equivalent.

Course Outline (subject to change)

Course Requirements

Homework sets (60%) and a take-home final examination (40%)

Open problems will be introduced throughout the semester. Students who solve any one of the open problems will automatically receive an A for the course.

General References

  • Yu. Nesterov: Introductory Lectures on Convex Optimization: A Basic Course. Kluwer Academic Publishers, 2004.

Schedule and Reading

Homework Sets

Last Updated: April 27, 2017