CS 760: Machine Learning

📍 Course Logistics

📍 Location

Morgridge Hall B2590

🕘 Time

Mondays & Wednesdays 9:30–10:45

👨‍🏫 Instructor

Misha Khodak

Email: khodak@wisc.edu

Office Hours: Mondays 10:45-11:45 & Tuesdays 1:30-2:30

👨‍💻 Teaching Assistants

Haotian Ma (hma232@wisc.edu)
Office Hours: Fridays 2-3 in MH 2513

Avi Trost (astrost@wisc.edu)
Office Hours: Wednesdays 3:30-4:30 in MH 2513

🔗 Course Links

Canvas Piazza Gradescope

📋 Course Policies

📊 Grading

The final grade will be calculated based on:

Homework: 30%
Midterm Exam: 30%
Final Exam: 40%

Regrade requests for both homeworks and exams must be raised within 72 hours after grades are returned. Graders reserves the right to regrade the entire homework and could potentially take points off.

📝 Homework

All homework assignments must be done individually. Cheating and plagiarism will be dealt with in accordance with University procedures (see the Academic Misconduct Guide for Students). For example, code for programming assignments must not be developed in groups, nor should code be shared. You are encouraged to discuss with your peers, the TA, or the instructor ideas, approaches and techniques broadly, but not at a level of detail where specific implementation issues are described by anyone. If you have any questions on this, please ask the instructor before you act.

Your lowest homework grade (of an anticipated 5-6 assignments) will be dropped. This is meant to be used to handle emergencies, and so extensions are extremely unlikely to be provided.

All solutions (written and typeset) must be submitted as PDFs. We will give five extra points for assignments typeset using LaTeX with the provided template. Starting with Homework 2, we will take off one point for assignments with question not matched to the Gradescope outline.

📚 Exams

Midterm Exam: Mid/Late October, TBD. Topics covered: all topics in lectures up to the exam; related slides and notes (unless specified otherwise).
Final Exam: 16 December 2025, 5:05PM - 7:05PM (Location TBD). Topics covered: all topics in the class, with a focus on those after midterm.

All exams will be conducted in-person. Please plan for exams at these times and let us know about any exam conflicts during the first two weeks of the semester. If an emergency arises that conflicts with the exam times, email us as soon as possible. Emergency exam conflicts will be handled on a case-by-case basis.

📖 Recommended Readings

There will be no required readings, but we strongly suggest you look at the suggested chapters provided with many of the lectures. Many of these will be taken from the following textbooks, which can be found online or accessed via UW-Madison:

Machine Learning by Tom Mitchell
Pattern Recognition and Machine Learning by Chris Bishop
Machine Learning: A Probabilistic Perspective by Kevin Murphy
Understanding Machine Learning: From Theory to Algorithms by Shai Shalev-Shwartz & Shai Ben-David
Deep Learning by Ian Goodfellow, Yoshua Bengio, & Aaron Courville
Foundations of Machine Learning by Mehryar Mohri, Afshin Rostamizadeh, & Ameet Talwalkar
Reinforcement Learning: An Introduction by Richard Sutton & Andy Barto

📅 Tentative Schedule

Date	Lecture	Slides	Readings	Notes
3 September	Course overview & logistics	slides	Jordan & Mitchell	Homework 0 out
8 September	Machine learning overview	slides
10 September	Supervised learning: nearest neighbors & decision trees	slides	Shalev-Shwartz & Ben-David 18
15 September	Supervised learning: evaluation	slides
17 September	Supervised learning: parametric modeling	slides	Mitchell 6.1-6.10; Murphy 3.1-3.3 & 3.5 Murphy 8.1-8.3 & 8.6	Homework 0 due Homework 1 out
22 September	Supervised learning: linear regression	slides	Bishop 3.1 & 4.3; Murphy 7.1-7.3 & 7.5 Breiman: The Two Cultures
24 September	Supervised learning: optimization	slides	Garrigos & Gower 1-3.1 Goh: Why Momentum Really Works
29 September	Unsupervised learning: clustering	slides	Shalev-Shwartz & Ben-David 22
1 October	Unsupervised learning: dimensionality reduction	slides	Shalev-Shwartz & Ben-David 23	Homework 1 due Homework 2 out
6 October	Neural network basics	slides	Goodfellow, Bengio, & Courville 6 Mohri, Rostamizadeh, & Talwalkar 8.3.1
8 October	Neural network training	slides	Goodfellow, Bengio, & Courville 7-8
13 October	Convolutional neural networks	slides	Goodfellow, Bengio, & Courville 9
15 October	Recurrent neural networks	slides	Goodfellow, Bengio, & Courville 10 Olah: Understanding LSTM Networks	Homework 2 due Homework 3 out
20 October	Midterm review	slides
22 October	Midterm
27 October	Language models	slides	Alammar: The Illustrated Transformer
29 October	Generative models	slides	Rogge & Rasul: The Annotated Diffusion Model
3 November	Learning theory	slides	Bishop 3.2
5 November	PAC learning	slides	Mohri, Rostamizadeh, & Talwalkar 2-3	Homework 3 due Homework 4 out
12 November	SVMs and kernels	slides	Mohri, Rostamizadeh, & Talwalkar 5-6
17 November	Science of deep learning	slides	Cohen: Central Flows
19 November	Reinforcement learning	slides	Mitchell 13
23 November	Reinforcement learning	slides	Mitchell 13	Homework 4 due Homework 5 out
1 December	Reinforcement learning	slides	Mitchell 13
3 December	Less-than-supervised learning	slides
8 December	Transfer learning	slides		Homework 5 due
10 December	Final review	slides