Do we really need overparameterization in deep learning? Rebekka Burkholz


Aktuell gibt es keine Neuigkeiten

Do we really need overparameterization in deep learning?

Deep learning continues to impress us with breakthroughs across disciplines and is a major driving force behind a multitude of industry innovations like ChatGPT. Most of its successes are achieved by increasingly large neural networks that are trained on massive data sets and still achieve zero training loss. This recent trend to overparameterize neural networks defies classic concepts of statistical learning theory that suggest to avoid overfitting by reducing the number of trainable parameters. We will look into recent explanations of this puzzling phenomenon, discuss related insights, and challenge the modern belief that scaling up neural networks is always the best way to move forward.
Are the simplest models always the best choice? And is counting parameters really the best way to measure model complexity? Please join the seminar if you enjoy thinking about this kind of questions.


Important Dates

* Kick-off meeting in the first week of the semester (tbd) (to be held online, via zoom).
* The reviews (and questions) must be submitted during the semester, one review per month.
* The presentations will be organized in a block format during the semester break (dates to be fixed at the kick-off meeting). Participation is mandatory.
* Hand-in of report: tbd, ideally one week after the block course.


* 2 short reviews: (each contributes 10% of your final grade): Write a short review (max 1 page) on one of the papers (not the one that you are presenting) that addresses the following questions:
    1. What is the problem addressed by the paper?
    2. What was done before, and how does the paper improve on previous work?
    3. What are the strengths and the limitations of the techniques in the paper
    4. What part of the paper was difficult to understand?
    5. What are possible improvements or extensions of the techniques in the paper?
* In addition to your review you will have to submit 3 questions that you will ask the presenter of the paper.
* Presentation: (40%). You will prepare and deliver a 20-30 min presentation (followed by 10 mins question/discussion) of the paper assigned to you. You will have the possibility to get feedback on your slides before the presentation.
* Seminar Paper: (40%) You will write a seminar paper on the topic that you have presented. It must not be longer than 6 pages, not counting references and appendices. Note that appendices are not meant to provide information that is absolutely necessary to understand the paper, but rather to provide auxiliary material. Papers can be shorter, but in general the provided page limit is a good indicator of how long a paper should be.

Datenschutz | Impressum
Bei technischen Problemen wenden Sie sich bitte an die Administratoren