CS/ECE/STAT-861: Theoretical Foundations of Machine Learning

Grading overview

• Scribing: 10%

• Homeworks: 35%

• Take-home exam: 30%

• Course project: 25%

Auditing: Students auditing the class need to complete only the scribing portion.

Scribing

Each student will be required to prepare scribed notes for  2 lectures. There will be around 2 scribes per lecture. (I may need to change this if the current enrollment falls significantly.)

Scribes should take careful notes in class, and prepare a LaTeX document written in full prose, understandable to a student who may have missed class. Scribes should include all steps of the proof, any intuitive explanations, and thoroughly check for typos before submitting. The latex document and source files should be submitted within two days of the lecture. After review, the scribed notes will be posted to the course website.

Instructions

• Please use this LaTex style file and this template for scribing lecture notes.

• While not mandatory, I strongly recommended that you use Overleaf to prepare the notes.

• After completing the notes, please invite me (kandasamy@cs{dot}wisc{dot}edu) as a collaborator on your overleaf project, and send me an email indicating that you have done so. The scribed lecture notes should be submitted within 2 days of the lecture.

• You may sign up in this spreadsheet either as Scribe 1 or Scribe 2.

• If you decide to drop the class before your scribe date, please delete your name from the scribe slot and email me. If you have enrolled, but are not sure about taking the class, please sign up for later classes (after Oct 6).

Homeworks

There will be 4–5 problem sets, which will be posted on Canvas. Homeworks will typically be due in class at the beginning of the lecture.

• If you cannot make it to class, please hand it over to me in person by 10.30 am (if I am not in my office, you may slide it under my door). If you are traveling, you may either hand it over to me ahead of time, or email me a pdf of your solution, typeset in LaTex, by 10.30am.

• Late submissions: Twenty percent of the homework value will be deducted for each day a homework is late. Exceptions will be made only for documented emergencies. Solutions for the homeworks will be posted within a week of the deadline. Students will receive no credit for submissions after solutions are posted.

• Students will receive 5 percent extra credit if their solutions are typeset fully using LaTex. If you choose to submit hand-written homeworks, please make sure your handwriting is legible. I will not spend undue effort trying to understand poor handwriting. If you are emailing me a pdf due to travel, the solution must be typeset in LaTex.

• As we will re-use questions in future offerings of this class, please do not release homework or exam questions outside of class or discuss them in public forums.

Policy on collaboration: The problem sets will generally be difficult. Unless explicitly stated otherwise, students are allowed (and encouraged) to collaborate in groups of size up to three on each problem. However, each student must write up solutions individually and name any collaborators at the top of each problem. Please read the university's policy on academic misconduct.

Take-home exam

The exam will be held from Tuesday 11/14/2023 12.01 AM – Friday 11/17/2023 11.59 PM. The length of the exam is 48 hours. Students can start the exam at a convenient time within this period, but must submit their solution by 11.59 PM on 10/27 and within 48 hours of the start time.

You may refer to any of your notes or the scribed lecture notes during the exam. However, unlike the homeworks, you are not allowed to refer to any other material or collaborate/discuss the questions with other students in class. Please read the university's policy on academic misconduct.

Students will receive 5 percent extra credit if their solutions are typeset in LaTex. If you choose to submit a handwritten exam, please make sure your handwriting is legible. I will not spend undue effort trying to understand poor handwriting.

Course project

You may do the course project individually, or work in pairs.

• Students should submit a project proposal by Friday 10/20/2023 in class. Proposals should be at most 2 pages in length and follow the Neurips format.

• Projects are due by Friday 12/8/2023 on canvas. The final report should be at most 8 pages in Neurips format. You may include an appendix with proofs and other ancillary material.

While you are allowed to have experiments/simulations, projects should have a significant theoretical component. You are encouraged to discuss your project ideas with me, but you are responsible for formulating your own research question and solution.