Curriculum Core

Machine Learning PhD students are required to complete one course in each of four different core areas: Mathematical Foundations, Probabilistic and Statistical Methods in Machine Learning, ML Theory and Methods, and Optimization.  With the exception of the Foundations and Data Models course, the requirements can be met with different courses in different schools.

Course offerings are subject to change. 

Mathematical Foundations of Machine Learning

This required course is the gateway into the program, and covers the key subjects from applied mathematics needed for a rigorous graduate program in ML. Particular emphasis will be put on advanced concepts in linear algebra and probabilistic modeling. This course is cross-listed between CS, ECE, and ISyE.

  • CS/CSE/ECE/ISYE 7750, Mathematical Foundations of Machine Learning (offered fall semesters)

 

Probabilistic and Statistical Methods in Machine Learning
  • ISYE 6412, Theoretical Statistics (offered fall semesters)
  • ECE/ISYE/CS/CSE 7751, Graphical Models in ML (offered spring semesters)
  • MATH 7251, High Dimensional Probability (offered spring semesters)
  • MATH 7252 High Dimensional Statistics (offered fall semesters)

 

Machine Learning Theory and Methods

This course serves as an introduction to the foundational problems, algorithms, and modeling techniques in machine learning.  Each of the courses listed below treats roughly the same material using a mix of applied mathematics and computer science, and each has a different balance between the two.  

  • CS 7545 Machine Learning Theory and Methods (offered spring semesters)
  • CS 7616, Pattern Recognition (rarely offered)
  • CSE/ISYE 6740, Computational Data Analysis (offered fall and spring semesters)
  • ECE 6254, Statistical Machine Learning (offered fall and spring semesters)
  • ECE 6273, Methods of Pattern Recognition with Applications to Voice (offered spring semesters)

 

Optimization

Optimization plays a crucial role in both developing new machine learning algorithms and analyzing their performance.  The five courses below all provide a rigorous introduction to this topic; each emphasizes different material and provides a unique balance of mathematics and algorithms.

  • ECE 6270, Convex Optimization: Theory, Algorithms, and Applications (offered fall semesters)
  • ISYE 6661, Linear Optimization (offered fall and spring semesters)
  • ISYE 6663, Nonlinear Optimization (offered fall and spring semesters)
  • ISYE 7683, Advanced Nonlinear Programming (offered spring semesters)