Machine Learning for Algorithm Design


A main component of this course is a research project. This project can be theoretically-focused, data-oriented, or a combination of both, on any topic broadly related to one (or more) of the four parts of the course. Ideas for how to choose a project will be discussed in class. Students will work on their project in groups of two. The main milestones are:

  • One page project proposal, due on 10/19, should include:
    • A clear description of the problem you are trying to solve
    • Related work
    • Motivation for why this is an interesting problem
    • Preliminary ideas and simple cases for your problem
    • Next steps: are you planning to develop a new model, prove theoretical results, construct an algorithm, run experiments?
    • Main goals for the project
  • Project update in class on 11/4, for each group:
    • Presentation (5 min), maximum of 5 slides
    • Questions (5 min)
  • 30 min meeting with the instructor for each group in November
  • Final write-up (6 to 10 pages), due on 12/13
  • Final presentation during last class on 12/14