Stat 546: Machine Learning in Data Science

Welcome!

This the official website of STAT 546: Machine Learning in Data Science. This course is redesigned in Fall 2025. To get started, you can read the Course Syllabus.

• Homework assignments are due at Wednesday 11:59PM CT. Late submission is allowed, but with penalty.
• All homework should be submitted (.pdf file) to gradescope. Please use entry code: NGZK34 to enroll.
• Course discussion forum and grades are available at Canvas. Our TA will check these once

Course Information

• Lecture Location: 305 Materials Science & Eng Bld
  • Time: Tue/Thur 11:00am - 12:20pm
• Office Hours:
  • (in person) Mon 2:30 - 3:30PM at CAB 137 (need to switch to Wed 2-3pm on the week of Sep 15, Oct 13, Nov 10 and Dec 8)
  • (zoom) Mon/Wed at 7PM [Zoom Link: 88910194092, pw:546]
  • Or make appointment via email: start your email title with “STAT546:”
• TA: Mehrdad Mohammadi [mehrdad3 at illinois dot edu]

Course Schedule

Our course consists of five major topics:

• Reproducing Kernel Hilbert Space
• Tree-based Ensemble Models
• Causal Inference Basics
• Personalized medicine
• Reinforcement Learning

Each topic spans about 2-4 weeks and the first two topics also serve as a foundation and preparation of tools for the later topics. For details please refer to the course page of each topic.

---

Announcements:

• (Oct 8): HW1 and HW2 solutions are posted.
• (Sep 5): There is an update of the office hours on the weeks of Sep 15, Oct 13, Nov 10 and Dec 8. The new time is Wed 2-3pm on these weeks, at CAB 137.
• (Aug 29): Homework 1 posted. Due Sep 10, 11:59PM CT.
• (Aug 18): The current version of the RStudio (version 2025.05.1-xxx) has a bug with Copilot and may freeze your RStudio. See this post. One solution is to install unpublished daily builds from here with versions 2025.05.2-xxx. This worked for me.