CSC 581A Project Details

As part of this course, every graduate student will complete a solo project with a significant theoretical component.

Types of projects

Below are suggestions for types of projects you could complete. The first set are research-oriented projects, which could involve: The second set are survey-oriented, such as:

Initial meeting to green-light your project

In early November, I'll meet with each of you to ensure that you have a sensible project that is at the right scale. For ideas/themes for projects, take a look at the "Project ideas" section below.

Presentation

For each project, there will be a 15 to 25 minute presentation (depending on the time available) to discuss your findings, plus a few minutes for questions. These presentations will happen in the last week of lectures.

Submission

Each of you also will submit a 3-5 page report, not including references. The maximum length is flexible depending on your project; for instance, if you engage in an interesting research topic that could lead to a paper, a longer writeup may be ideal. For your report, please use the LaTeX style file and template below (this is just to get the geometry right, e.g. margins, font size, line spacing):

Your project writeups are due (via email) by Thursday December 16th, 11:59pm PST. Please submit on time. Any late submissions (even late by one minute) will incur a nontrivial penalty.

Project ideas

Below are some papers in various areas to help you think about project ideas; I may update these soon to include a few other areas.

Deep learning and generalization

Active learning

Transfer learning and lifelong learning
  Fully online lifelong learning:   Lifelong learning of PAC learning tasks:
Learning under corruption

PAC-Bayesian bounds
  Margin bounds:   Generalized PAC-Bayesian bounds:   PAC-Bayesian bounds with faster rates and unbounded losses:
Compression schemes

Learning at faster rates
  Massart and Tsybakov noise:   Efficient learning:
Algorithmic stability
  Connection to cross-validation:
Private learnability as well as its connection to online learnability

Online learning