Topics in Optimization: Mathematical Foundations of Machine Learning
Andrew Warren (University of British Columbia)Sep 3, 2025 — Dec 3, 2025
About the course
This course is a bridge into the machine learning literature for graduate students in mathematics. Compared to existing course offerings in our neighbouring departments (mainly https://www.cs.ubc.ca/~dsuth/532D/23w1 (https://www.cs.ubc.ca/~dsuth/532D/23w1)) we will assume that you know somewhat more analysis, but prior coding experience will not be required. Briefly, the learning objectives are:
- understand the different “learning paradigms” considered in ML (supervised learning, unsupervised learning, reinforcement learning, etc.) and their relation with existing statistical theory
- be comfortable with mathematical tools (eg. kernel methods) which appear commonly in the ML literature but are not well known among pure mathematicians
- see some natural connections between ML theory and: optimization/calculus of variations, measure theory, PDE, etc
- gain fluency reading ML papers (which can be less trustworthy than pure math papers)
- start to think about how to bring your area of mathematical expertise to bear on ML problems.
Registration
This course is available for registration under the Western Dean's Agreement. To register, you must obtain the approval of the course instructor and you must complete the Western Dean's agreement form , using the details below. The completed form should be signed by your home institution department and school of graduate studies, then returned to the host institution of the course.
Enrollment Details
- Course Name
- Discrete Optimization
- Date
- Sep 3, 2025 — Dec 3, 2025
- Course Number
- MATH 604
- Section Number
- Section Code
Instructor(s)
For help with completing the Western Dean’s agreement form, please contact the graduate student program coordinator at your institution. For more information about the agreement, please see the Western Dean's Agreement website
Other Course Details
Class Schedule
- TBA
Remote Access
Remote access to this course will be via zoom. The delivery mechanism will be either blackboard or via tablet depending on available rooms. A PDF textbook and/or research article readings will be distributed in advance of each class.
Availability
This course may be open to students from universities outside of the PIMS network.