Ask HN: Has anyone tried to search for new, basic machine learning operations?

E.g. primitive operations like convolution and pooling.

From Neural Architecture Search: A Survey[0], first published in 2018:

"Moreover, common search spaces are also based on predefined building blocks, such as different kinds of convolutions and pooling, but do not allow identifying novel building blocks on this level; going beyond this limitation might substantially increase the power of NAS."

I wonder now if somebody tried that since this was written or if anybody has some thoughts about the feasibility of this idea.

We've been using these methods for years. I doubt the first few breakthroughs are the most optimal possible.

[0]https://arxiv.org/abs/1808.05377