If you are unable to enroll, please send me an email (nidhih@ualberta.ca).
We will start with an introduction to basic tools required for understanding foundational results in machine learning theory. We will then use the same approach to understand theoretical results in robust and trustworthy machine learning, including stability, privacy, and fairness.
For the first part of the course we will cover basic tools, relying mostly on the first few chapters of the textbooks by Tong Zhang and Francis Bach listed below. For the second part of the course, we will use the instructor’s lecture notes and foundational research papers.
Students are expected to follow mathematical proofs, deal with expressions involving probabilities and have a working knowledge of calculus and linear algebra.
A good understanding of basic probability, linear algebra and convex optimization is expected. The textbook A Second Course in Probability Theory is highly recommended. The book is available online and also in book format. Chapters 1, 3, 4, and 5 are most useful for us.