The goal of this seminar course is to study the computational and statistical ideas underlying (or at least related/adjacent to) large language models.
Topics may include the following.
Readings from research papers and other sources will be made available on the course website.
The emphasis of this course is on theoretical/mathematical foundations, although some of the motivations come from experiments and real systems.
A course in computational learning theory or machine learning theory (e.g., COMS 4252, COMS 4773), theoretical statistics/neuroscience, or equivalent/similar technical preparation.
Please fill out the following questionnaire if you are interested in enrolling: https://forms.gle/KZpj5wxWXFsziZow5. If you cannot access the form, please see the questions here and email me your answers.
It is possible that some people won't be able to get on the waiting list immediately due to some registration restrictions, but I think these restrictions will eventually be lifted. (I will make sure to reserve some seats for people who are only able to get on the waiting list late in this process.)
Reading responses (30%), paper presentation and discussion (30%), course project (40%)