Universal Approximation of Functions on Sets (JC)

JC - Journal Club

Title:
Universal Approximation of Functions on Sets (2021)

Authors:
Edward Wagstaff, Fabian B. Fuchs, Martin Engelcke, Michael A. Osborne, Ingmar Posner

This paper will be presented by:
Zach Baker

About the Paper:
This paper is a little bit more math-heavy than what we usually cover. This paper goes over the requirements for universal approximation for sets in a formal and rigorous way. The latent space isn't treated as a black box here, which I find to be a breath of fresh air compared to the more complicated methods of GANs and language models. The algorithm used here is called 'Deep Sets,' and looks a bit like the attention mechanism found in transformers.

Paper: https://arxiv.org/abs/2107.01959

Spots are limited to keep the discussions organized.

Austin Deep Learning Journal Club is group for committed machine learning practitioners and researchers alike. The group meets every first Tuesdays of each month to discuss research publications. The publications are usually the ones that laid foundation to ML/DL or explore novel promising ideas and are selected by a vote. Participant are expected to read the publications to be able to contribute to discussion and learn from others. This is also a great opportunity to showcase your implementations to get feedback from other experts.
Anyone can suggest and vote for the next paper on Austin Deep Learning slack work space (#paper_group channel): https://austin-deep-learning-slack.herokuapp.com/
Please only RSVP if you are certain that you will be participating.

What to bring:
A copy of the paper (either digital or hardcopy)