Course project

The project is intended to engage you in a non-trivial application of computation and/or optimization methods in statistics/data science. We encourage you to combine the project with your research or a personal project. You may complete the project in teams of up to 3 students. We expect larger teams to deliver a more substantial project than smaller teams.

The deliverables are a project proposal, a draft report, a peer review, and a final report. Your grade on the final project is a combination of your grades on the deliverables: 10% project proposal, 10% draft report, 10% peer review, 70% final report.

Coming up with a project

Most projects fall into one of three types:

• original research: we encourage you to combine your research with the course project;
• review/survey: review/survey a body of (recent) research;
• reproduction: reproduce the results in a (research) paper;

Before starting work on a project, make sure it is novel; i.e. the project should fill a gap in the literature (e.g. there are no recent review papers on the same topic). After coming up with a project idea, first do a literature review to gauge the novelty of the idea, then discuss the idea with the course staff.

The following guidelines on the deliverables are intentionally vague (to allow the widest variety of projects). Please ask the course staff about guidelines specific to your project.

Project proposal

• The proposal is due at noon ET on Fri, Feb 24. It is intended to get you started on the project and solicit feedback from the course staff.
• The proposal must include the title of the project, the names of the team members. It should be no more than two pages (excluding references). Please follow the guidelines for mathematical writing.
• The goal of the project proposal is similar to that of a grant proposal. A good proposal should convince the course staff that (i) the project is worth doing (e.g. if the original authors provide code that reproduces the results, then it is not worth reproducing the results again), and (ii) you can complete the project. For (i), the best way is to review related work in the area and identify the gap that your project intends to fill. For (ii), the best way is to start working on the project. This helps you identify issues that may arise and propose solutions.
• The proposal is graded on the same 1-4 scale as the problem sets.

Draft report and peer review

• The draft report is due at noon ET on Fri, Mar 31. It is intended to solicit feedback from your classmates, so the draft should be as close to the final report as possible. Please follow the guidelines for mathematical writing.
• The peer review process is double-blind; i.e. the reviewer(s) are hidden from the author(s) and vice versa. Thus the draft report must be anonymous; i.e. do not include team member names in the draft report.
• The draft report is graded on the same 1-4 scale as the problem sets. If a draft report is not anonymous, then 1 pt (out of 4 pts) will be deduced from its score.
• The peer review of your assigned project is due on noon ET on Fri, Apr 7. It is intended to provide constructive feedback to your classmates. The review should include a summary of the report (to show your comprehension) and any comments and suggestions. For examples of peer reviews, see the reviews for submissions to NeurIPS 2022 on OpenReview.
• The peer review must be anonymous; i.e. do not include reviewer names in the peer review.
• The peer review is graded on the same 1-4 scale as the problem sets. If a peer review is not anonymous, then 1 pt (out of 4 pts) will be deduced from its score.

Final report

• The final report is due on noon ET on Fri, Apr 14. It should be no more than 8 pages (excluding the contributions section, references, and any appendices).
• The report should have (but is not limited to) the following 5 sections: introduction, related work, methods, results, conclusion/discussion. The 5 preceding sections will be graded on their contents (4 pts) and their presentation (4 pts) on the same 1-4 scale as the problem sets. For details on the contents of each section, see the Stanford CS 229 final report guidelines.
• We expect an “A” report to be similar to a workshop paper in terms of its clarity (but less comprehensive in terms of its scope). For examples of well-written reports, see Stanford’s CS 229 final projects.
• If you are working on a project as part of a team, you must also include a contributions section at the end of the report (where acknowledgements usually appear) describing the contributions of the team members. If there are discrepancies among the contributions of the team members, the grades will be adjusted.
• You must submit a PDF file of your project report and an archive of (properly commented) code that reproduces any computer output in the project report on Canvas. The report must be typeset.