Nihar B. Shah

10-715 Fall 2023: Advanced Introduction to Machine Learning

This course is designed for Ph.D. students whose primary field of study is machine learning, or who intend to make machine learning methodological research a main focus of their thesis. It will give students a thorough grounding in the algorithms, mathematics, theories, and insights needed to do in-depth research and applications in machine learning. The topics of this course will in part parallel those covered in the general graduate machine learning course (10-701), but with a greater emphasis on depth in theory.

IMPORTANT NOTE: Students entering the class are expected to have a pre-existing strong working knowledge of linear algebra (e.g., mathematical representation of subspaces, singular value decomposition), probability (e.g., multivariate Gaussians, Bayes' rule, conditional expectation), and calculus (e.g., derivative of a vector with respect to another vector), and programming (we'll mostly be supporting Python). This class is best for you if you have machine learning at the CORE of your studies/research, and want to understand the fundamentals. This class will be HEAVY and will move FAST. If machine learning is an auxiliary component of your studies/research or if you do not have the required background, you may consider the general graduate Machine Learning course (10-701) or the Masters-level Machine Learning course (10-601). Click here for an ML course comparison. Note that machine learning itself is NOT a prerequisite for this course.
Also note that by departmental policy, this course is open only to graduate students (5th year masters are allowed).

Waitlist: The waitlist will be processed near end of summer.

Time and location: The class is scheduled for Monday and Wednesday 2pm to 3.20pm in POS 152. We will reserve Fridays for recitations, which will be held 2pm to 3.20pm in the same location.

Units: 12

Instructor: Nihar B. Shah

Grading and other logistics: Will be discussed in the first lecture.

Textbook: [SB] Understanding Machine Learning: From Theory to Algorithms by Shai Shalev-Shwartz and Shai Ben-David (available online)

Last year's videos: The course content is similar to the offering in previous years. You can find previous years' videos here.

Syllabus and lecture schedule. Note that most lectures will be taught on the "board'', and hence there are no "slides''.

Date	Topic	References/Remarks
PART I: DEPTH
Aug 28	Logistics and introduction to introduction to ML	SB chapter 2
Aug 30	Perceptrons: Hope, hopelessness, and hope again	SB chapter 9
Sep 1	Optimization for ML [Note:This is a regular lecture on Friday to make up for Sep 21]	Notes
Sep 6	Support vector machines	SB chapter 15
Sep 8	Recitation: Optimization
Sep 11	Kernel methods 1	SB chapter 16
Sep 13	Kernel methods 2	SB chapter 16
Sep 15	Recitation: Tail bounds
Sep 18	Learning theory 1	SB Chapters 2 - 5
Sep 20	No class [Make up class was on Sep 1]
Sep 22	Recitation: Linear regression, Logistic regression
Sep 25	Learning theory 2	SB Chapters 2 - 6
Sep 27	Learning theory 3	SB Chapters 2 - 6
Sep 29	Recitation: MLE and MAP
Oct 2	Learning theory 4	SB Chapters 6 - 7
Oct 4	Midterm	All material in previous lectures
PART II: BREADTH
Oct 9	Neural networks 1: Introduction. Also, midterm discussion.	SB Chapter 20
Oct 11	Neural networks 2: Representation power
Oct 23	Neural networks 3: Training, automatic differentiation, CNNs, etc.
Oct 25	Theory paper dissection
Oct 30	Model complexity, cross-validation bias-variance tradeoff, interpolation regime, and Neural networks 4 (neural architecture search)
Nov 1	(Large) language models
Nov 6	Unsupervised learning: Clustering, Dimensionality reduction, Diffusion models	SB Chapter 22, 23
Nov 8	Decision trees, random forests, bagging, bootstrapping	SB Chapter 18
Nov 13	Online learning	SB Chapter 21
Nov 15	Semi-supervised learning, Active learning, Multi-armed bandits	Transductive SVM, Active learning, Multi-armed bandits, Ranking via MABs
Nov 20	Reinforcement learning 1	Survey
Nov 27	Reinforcement learning 2 and RL from Human Feedback (RLHF)
Nov 29	Applied paper dissection
Dec 4	Graphical models, Causality, Fairness, Interpretability, Alignment	Graphical models, Hiring example, Paper 1, Paper 2
Dec 6	Final exam

Accommodations for Students with Disabilities: If you have a disability and have an accommodations letter from the Disability Resources office, I encourage you to discuss your accommodations and needs with me as early in the semester as possible. I will work with you to ensure that accommodations are provided as appropriate. If you suspect that you may have a disability and would benefit from accommodations but are not yet registered with the Office of Disability Resources, I encourage you to contact them at access@andrew.cmu.edu.