On: The FFT Strikes Back: An Efficient Alternative to Self-Attention

[1024core]

> Why not, for example, a wavelet transform.

That is a great idea for a paper. Work on it, write it up and please be sure to put my name down as a co-author ;-)

[monkfish328 → 1024core]

Or for that matter, a transform that's learned from the data :) A neural net for the transform itself!

[spot5010 → monkfish328]

That would be super cool if it works! I’ve also wondered the same thing about activation functions. Why not let the algorithm learn the activation function?

[porridgeraisin → spot5010]

This idea exists (the broad field is called neural architecture search), although you have to parameterize it somehow to allow gradient descent to happen.

Here are examples:

https://arxiv.org/abs/2009.04759

https://arxiv.org/abs/1906.09529

[FuckButtons → spot5010]

Mostly because of computational efficiency irrc, the non linearity doesn’t seem to have much impact, so picking one that’s fast is a more efficient use of limited computational resources.