CSCI 6220/4030 Project Details, Fall 2019

As teams, you will give a 20 minute presentation of an interesting or cool result or an algorithm (or class of algorithms) from a course-relevant technical or survey paper to the class; if your research is relevant, that could also be the topic of your presentation.

This can be material that requires no background beyond general knowledge of CS, or more niche/applied knowledge; in the latter case, you should quickly explain the relevant concepts and background. See the "What is Research?", "Giving Talks", and "Reading Papers" slide decks from the 2019 CS Grad Skills Seminar.

Grading Rubric and Deadlines

Task Due date Percentage of grade
Paper selection 11:59pm, October 28 10
Discuss paper with me by 5pm, November 22 40
Deliverables start of class, December 2 10
In-class 20 minute presentations December 2 or 5 40

Paper selection

You group must get my approval to present your research or the paper you have chosen. This means I need to be informed of your decision and have verified that it is an appropriate choice by the deadline.

Some choices of topics—biased towards my own interests in ML, linear algebra, and convex optimization, so you are welcome to make choices other than these:

Discuss paper with me

See my suggestions on reading papers from the 2019 CS Grad Skills Seminar. All of your group must discuss your research/paper in a group meeting with me by the deadline. Address all the points I raise below, to show that you will be able to give a quality presentation. Justify your choice of empirical evaluations and baselines. I highly suggest you have your experiments done so that we can discuss them.

Schedule this meeting at least the week before the deadline: I will not be able to meet with every group on the day of the deadline. If you have difficulties with your paper, meet with me to resolve them well before your scheduled formal discussion.


These should be submitted in a single github/gitlab repo for each project. The experimental results presented in your talk must be easily reproducible given access to this repo.

In-class presentation

See Prof. Anshelevich's suggestions on giving a good talk from the 2019 CS Grad Skills Seminar. Address the following points in your presentation to receive full credit for this portion.