STA 9890 - Handouts and Additional Notes
Supplemental course notes and links to useful external resources will be posted here. These will be updated repeatedly throughout the semester without fanfare, so please check here often.
Supplemental Lecture Notes
Week 1 - Fundamentals of ML: I. Introduction to ML (2026-01-28)
Week 2 - Fundamentals of ML: II. Linear Algebra Foundations (2026-02-04)
The YouTube channel “3Blue1Brown” makes excellent videos explaining mathematical concepts. A recent entry discusses gradient descent in the context of Neural Networks. At this point in the course, our focus is still on simpler (convex) methods, so not all of this will be directly applicable, but it is still a useful summary and gives helpful background on how gradient methods remain at the heart of all modern ML.
You may also find value in 3Blue1Brown videos on Linear Algebra and on Probability.
Of these, the following are likely to be particularly useful in this course:
- Vectors
- Linear Transformations
- Matrix Multiplication
- Inverses, Rank, and Null Space
- Dot Products and Duality
- Eigenvectors and Eigenvalues
- Bayes’ Theorem
though you don’t need to watch all of these immediately.
In this course, we will apply calculus techniques (mainly differentiation) to functions \(\mathbb{R}^{p} \to \mathbb{R}\). The website matrixcalculus.org/ is helpful for this work.
Week 3 - Fundamentals of ML: III. Accuracy and Loss in ML (2026-02-11)
Week 4 - Fundamentals of ML: IV. Optimization & Simulation in ML (2026-02-18)
Week 5 - Supervised Learning: I. Regularization & Shrinkage (2026-02-25)
Week 6 - Supervised Learning: II. Penalized Regression (2026-03-04)
Week 7 - Supervised Learning: III. Generative Classifiers (2026-03-11)
Week 8 - Supervised Learning: IV. Discriminative Classifiers & Non-Linear Methods (2026-03-18)
Week 9 - Supervised Learning: V. Trees & Ensemble Methods (2026-03-25)
Week 10 - Unsupervised Learning: I. Introduction (2026-04-15)
Week 11 - Unsupervised Learning: II. Clustering (2026-04-22)
Week 12 - Unsupervised Learning: III. Dimension Reduction & Manifold Learning (2026-04-29)
Week 13 - Unsupervised Learning: IV. Generative Models (2026-05-06)
Tests and Solutions
Mid-semester tests and solutions will be posted here after the exam.
Additional Materials
Older notes, homework problems, and exam from prior offerings of this course can be found using the Prior Offerings tab above. Note that the syllabus of this course has changed slightly from semester to semester, so the format and content of exams may not map cleanly onto this semester.
Additional solutions will not be provided if not already posted, but I am happy to discuss individual problems in office hours or on the course discussion board.