COMS 4772 is an advanced graduate-level course on machine learning theory. This semester, the course will cover theoretical aspects of high-dimensional data analysis and statistical machine learning.


You should be familiar with the basic principles of machine learning, although this alone is not sufficient. You must have a solid background in multivariate calculus, linear algebra, basic probability, and algorithms. You must have general mathematical maturity and be comfortable with mathematical writing (e.g., mathematical arguments, derivations, and proofs). This is a theory course, so you will be expected to understand and produce mathematical arguments and rigorous proofs.


Readings will be assigned from notes, books, and research papers available on the web. This includes readings from the following texts:

Course requirements

  • Homework assignments (50% of the course grade).
  • Project and oral presentation (50% of the course grade).

Homework write-ups

Each homework write-up must be neatly typeset as a PDF document. You can use LaTeX or any other system that produces typesetting of equal quality and legibility (especially for mathematical symbols and expressions). Ensure that that the following appear at the top of the first page of the write-up:

  • your name,
  • your UNI, and
  • the UNI’s of any students with whom you discussed the assignment.

Submit your write-up as a single PDF file on Courseworks by 11:59 PM of the specified due date. It is your responsibility to ensure that the submission is successfully received by Courseworks.

For information and tips on using LaTeX, see the Introduction to LaTeX by Rocco Servedio, The Not So Short Introduction to LaTeX2e by Oetiker et al, the Short Math Guide for LaTeX by the American Mathematical Society, and the LaTeX Wikibook.


No late assignments will be accepted without valid medical/family emergency, as authenticated by your academic adviser (and a physician, if applicable).

Disability services

If you require accommodations or support services from Disability Services, comply with their policies and make any necessary arrangements within the first two weeks of the semester.

Academic rules of conduct

You are expected to adhere to the Academic Honesty policy of the Computer Science Department, as well as the following course-specific policies.


You may discuss the course material and the homework problems with each other in small groups (2-3 people). You must list all discussion partners in your write-up. Discussion of homework problems may only include problem clarification and high-level verbal discussion of possible approaches. You may not discuss solutions or solution details. Discussion must not go as far as one person telling the others how to solve the problem. You should not take any notes away from these discussions. You must write up your own solutions independently. You may not look at another student’s notes, solutions, or write-up (whether partial or complete).

Outside references

Outside reference materials and sources (i.e., texts and sources beyond the assigned reading materials for the course) may be used only if explicitly permitted, i.e., with written permission from the instructor. Such references must be appropriately acknowledged in the write-up. You must always write up your solutions in your own words.

  • Sources obtained by searching the internet for answers or hints on assignments are never permitted.
  • Texts and sources on mathematical prerequisites (calculus, linear algebra, probability, algorithms) are fine to use. (This is your explicit written permission to use such sources.) If you need to look up a result in such a source, you should give a citation.
  • If, in the course of your studying (not while working on a homework assignment), you inadvertently come across the solution to a homework problem, simply acknowledge this source in your write-up (and the circumstance), but do your best to produce a solution without looking at the source. You must, of course, write your solution in your own words.


Violation of any portion of these policies will result in a penalty to be assessed at the instructor’s discretion. This may include receiving a zero grade for the assignment in question AND a failing grade for the whole course, even for the first infraction.

Course materials (lecture slides, lecture notes, homework assignments, homework solutions, exams, exam solutions) are copyrighted and may not be re-distributed without explicit permission from the instructor.