COMS 4772 Fall 2020 (Advanced Machine Learning)

Course information

  • Time: Mon/Wed 8:40am–9:55am
  • Venue: TBD
  • Instructor: Daniel Hsu
  • Teaching/course assistants: TBD
  • Office hours: TBD
  • External links:



Course description

COMS 4772 (“Advanced Machine Learning”) is a graduate-level course on “advanced topics” in machine learning. By “advanced topics”, we mean topics that were not covered (at all or in depth) in COMS 4771 (“Machine Learning”).

Course topics

A tentative list of topics is as follows:

  • Dimension reduction
    • Random projections, hashing/sketching, spectral analysis
  • Optimization
    • Gradient descent, coordinate descent, stochastic optimization
  • Semi-supervised learning
    • Regularization methods, co-training / multi-view methods
  • Exploration
    • Multi-armed bandits, contextual bandits, active learning

(This list is subject to change.)


It is important to have taken a graduate-level course in machine learning or learning theory (e.g., one of COMS 4252, COMS 4771, COMS 4773). We’ll be building on the basic ideas developed in those courses. It is also important to have taken the prerequistes for those courses, which include multivariable calculus, probability, and linear algebra. Please contact the instructor if you have any questions about prerequisites.


The overal course grade will be based 60% on homework and 40% on the final project.

Please submit all assignments by the specified due dates. Extensions are generally only granted for medical reasons. (Please ask your academic advisor to confirm documentation from a physician / medical practitioner, and then ask them to email me their confirmation.)

Please submit your written assignments as PDF documents compiled using LaTeX (or a similar system) with bibliographic references included as necessary (e.g., using BibTeX). This will make grading much easier! If you have not used LaTeX before, or if you only have a passing familiarity with it, it is highly recommended that you read and complete the lessons and exercises in The Bates LaTeX Manual.

Final project

The final project is an opportunity to engage more substantially with one or more of the topics of the course. You are free to pick any topics you like, within reason. You may work individually or in pairs. The expectation for projects done in pairs in naturally higher than for those done individually.

Examples of projects include:

  • Empirical project: Implement an algorithm and conduct experiments to test hypotheses about the algorithm. This is ideal for students who have specific applications (and datasets) of interest.
  • Theory project: Prove a new and interesting theoretical result in a new or existing model. You can be ambitious, but do also aim for something interesting to show by the end of the semester. For example, a perfectly reasonable project is to find a simpler proof of an existing but complicated result.
  • Some combination of the above.

You will need to submit a brief project proposal (about 1 page should suffice), describing the project type, the chosen topic, the goals of the project, and the concrete steps/milestones to achieve the goals. This should be submitted by email to the course instructor at least 7 weeks before the end of the semester.

By the end of the semester, you will need to submit a brief project report. Please try to limit its length to at most 8 pages.

Disability services

If you require accommodations or support services from Disability Services, please make necessary arrangements in accordance with their policies 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.

Collaboration on homework assignments

You are welcome and encouraged to discuss homework assignments with fellow students. Your discussions should respect the following rules.

  • You must first make a serious effort to solve the problem yourself before discussing with another student.
  • Discussion about a homework problem can only take place with at most two other students, and only with students who have not already solved the problem.
  • Discussion about a homework problem may include brainstorming and verbally discussing possible solution approaches, but must not go as far as one person telling others how to solve the problem.
    • You may not take any notes (whether handwritten or typeset) from the discussions.
    • Written “discussions” (e.g., over messaging platforms, email) are not allowed.
  • You may not look at another student’s homework write-up/solutions (whether partial or complete).
    • You may not show your homework write-up/solutions (whether partial or complete) to another student.
  • You must write-up your solutions by yourself.
  • You must list all discussants in your homework write-up.

Use of outside references on homework assignments

Outside reference materials and sources (i.e., texts and sources beyond the assigned reading materials for the course) may be used on homework assignments only if given explicit written permission from the instructor and if the following rules are followed.

  • Any outside reference must be acknowledged and cited in the homework write-up.
  • Sources obtained by searching the literature/internet for answers or hints on homework assignments are never permitted.
  • You are permitted to use texts and sources on course prerequisites (e.g., a linear algebra textbook).
    • If you need to look up a result in such a source, provide a citation in your homework write-up.
  • If you inadvertently come across a solution to (or substantial hint about) a homework problem, you must:
    • acknowledge this source and document the circumstance in your homework write-up;
    • produce a solution without looking at the source; and
    • as always, write your solution in your own words.
  • If you have already seen one of the homework problems before (e.g., in a different course), please re-solve the problem without referring to any previous solutions.
    • In your write-up, please also indicate that you had seen the problem before. (You won’t lose any credit for this; it would just be helpful for us to know about this fact.)


Violation of any portion of these policies will result in a penalty to be assessed at the instructor’s discretion (e.g., a zero grade for the assignment in question, a failing letter grade for the course). All violations are reported to the relevant dean’s office.

Getting help

You are encouraged to use office hours and Piazza to discuss and ask questions about course material and reading assignments, and to ask for high-level clarification on and possible approaches to homework problems. If you need to ask a detailed question specific to your solution, please do so on Piazza and mark the post as “private” so only the instructors can see it.

Questions, of course, are also welcome during lecture. If something is not clear to you during lecture, there is a chance it may also not be clear to other students. So please raise your hand to ask for clarification during lecture. Some questions may need to be handled “off-line”; we’ll do our best to handle these questions in office hours or on Piazza.