It turns out that transformers have a learning mechanism similar to autodiff but better since it happens mostly within the single layers as opposed to over the whole graph. I wrote a paper on this recently https://arxiv.org/abs/2302.01834v1. The math is crazy.
Can you explain like I'm 5 why this matters distinctly from how transformers are normally trained with autodiff and what its possible applications are?
The paper speculates that it is analogous to gradient descent and empirically confirms it is similar in behavior, but it is not a rigorous proof of any kind.
The momentum experiment they made also does not seem related. E.g. it just adds past values to V, which extends the effective context length.
Match is a bad word, the don’t match, they are duals. The residual stream aka identity mapping needs to be the identity of the attention mechanism as the attention mechanism learns.
But this is the same for all residual streams, not just those in transformers.
Gradient descent is just how neural networks (including auto-encoders) optimize parameters to minimize the loss function. They do this using derivatives to descend down the slope of the function. Autodiff is one way to compute the derivatives. Maybe we’re saying the same thing.
