10-715 Fall 2024: 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 terms of theory (mathematical guarantees and proofs).

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 or makeup classes, 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 (for part of the course): [SB] Understanding Machine Learning: From Theory to Algorithms by Shai Shalev-Shwartz and Shai Ben-David (available online)

Syllabus and lecture schedule. Note that most lectures will be taught on the board.
Date Topic
Aug 26Logistics and introduction to introduction to ML
Aug 28Perceptrons: Hope, hopelessness, and hope again
Aug 30Optimization for ML
Sep 4Support vector machines
Sep 6Recitation: Optimization
Sep 9Kernel methods
Sep 11Learning theory 1
Sep 13Recitation: Tail bounds
Sep 16Learning theory 2
Sep 18Learning theory 3
Sep 20Recitation: MLE and MAP
Sep 23Learning theory 4
Sep 25Neural networks 1: Introduction, representation power
Sep 27Recitation: Linear regression, Logistic regression
Sep 30Midterm
Oct 2Neural networks 2: representation power, training, CNNs, Resnets
Oct 7Neural networks 3, model selection, bias-complexity tradeoff, interpolation regime
Oct 9Language models, attention mechanisms, transformers 1
Oct 21Attention mechanisms, transformers 2
Oct 23Attention mechanisms, transformers 3
Oct 28Attention mechanisms, transformers 4
Oct 30Transformers 5: Recent results
Nov 4Online learning
Nov 6Multi-armed bandits, Reinforcement learning 1
Nov 11Reinforcement learning 2
Nov 13Reinforcement learning 3; Graphical models and Causality 1
Nov 18Graphical models and Causality 2
Nov 20Diffusion models 1
Nov 25Diffusion models 2
Dec 4Final 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.