If you are interested in a qualifying paper with me, please email me to schedule a one-on-one meeting. The subject line of your email should start with "[Qualifying Paper]" to ensure I don't accidentally miss it. Come to the meeting prepared to discuss:
To ensure a productive meeting, please spend some time reviewing the paper before we meet.
The qualifying papers I've listed below are representative of my research interests, which broadly encompass many sub-areas of machine learning:
Within the realm of neural networks, my primary focus includes uncertainty quantification, robustness under covariate shift, theoretical models of overparameterization/fine-tuning, and connections to Bayesian inference. I'm also open to supervising qualifying papers on generative models (though you'll need to propose your own paper).
In general, I aim to supervise projects (and students) who are interested in either theoretical or methodological projects. Consider which research style you would like to pursue under my supervision. (In either case, expect to do both math and coding!) I'm also happy to work with students who want to relate/apply/extend one of the qualifying papers to a specific subject domain.
The final report for your qualifying paper will comprise two parts: (1) an extended review demonstrating your comprehension and critical evaluation of the paper, and (2) a mini-research project. Part 1 (the extended review) should take 2-3 weeks, and Part 2 (the project) should take 3-4 weeks.
The extended review should be divided into three sections:
Write a review of the paper as if you were on the program committee for a conference/journal. This exercise will help you think critically about the paper, and it will prepare you for future reviewing tasks. Your review should include the following:
This section should exhibit your grasp of the paper's technical content. Expect to review some related literature, as you should be able to contextualize the paper within the broader subfield. Address the following prompts in your summary:
This section should demonstrate your ability to think creatively about research. Brainstorm a generalization, extension, or novel application of the paper's content. Dreaming too big is better than dreaming too small: aim for a project with potential for publication or inclusion in your thesis. (I'll help you scope whatever you come up with into a 3-4 week mini-project.)
Your proposal should (1) describe the area of opportunity, (2) propose a method/approach, (3) identify expected technical challenges/bottlenecks, and (4) predict potential impact.
After completing a draft of your extended review, we'll meet one-on-one to define a 3-4 week project based on your proposal. You will turn in a 4+ page report along with associated code and data. The content of the project will depend on the style of the paper
Workflow expectations: My research approach tends to be highgly iterative, and I anticipate the same for our mini-projects. Initial project ideas will likely require modification to be fruitful. Be prepared to pivot or adjust your project, perhaps more than once.
In my opinion, a good researcher knows when to "fail fast." Most research ideas don't work, so figure out the fastest way to evaluate whether your ideas are likely to be dead ends. Design a minimal experiment/derivation for quick evaluation. If results seem promising in a week or two, continue pursuing the idea. Otherwise, adapt or pivot.
I expect you to check in with me at least once (ideally more) over the course of your project. Share (1) early results indicating your approach's viability and (2) your plan to pivot or adapt based on those results. Slack communication is preferred, but I'm always happy to meet in person if you want to bounce ideas off of each other.
Formatting: Submit the report as a GitHub repository, using the template at https://github.com/ben-br/qp-template/. The template includes a LATEX style file that should be used for the report. (Detailed instructions for usage can be found in the repository’s README file.) Ensure that the experimental results are reproducible. Write reusable/documented/well-commented Python code, and publish the code in a GitHub repo that I have access to. I should easily install and run your experiments.
As outlined in the assessment form, your evaluation will be based on: (1) your overall comprehension, (2) your ability to "go beyond," and (3) your work habits/reporting/communication skills. The extended review should showcase your understanding, while the mini-research project should demonstrate your creative thinking and ability to "go beyond."
The qualifying paper also gives me the chance to gauge your research potential and our compatibility in a mentor-mentee dynamic. I will not judge you based on how good your project results are. Rather, I will evaluate you on the following:
If a paper is crossed out, then it is no longer available.
(Although this paper is about kernel machines more generally, I am interested in applying some of its techniques to neural network ensembles. You should consider this paper if you are interested in deep learning theory. )
Many of these links have been shared by other faculty members as well:
Many parts of this document were derived/adapted/copied from Ben, Trevor, Marie, and Daniel. Thanks all!