[mvcalder]

Whenever this topic comes up I like to provide a citation to some work I've done:

https://towardsdatascience.com/gradient-kernel-regression-e4...

Not out of vanity (ok, a little) but because I think the idea has importance that has not been fully explored. The article's Bayesian perspective may be the whole story but somehow I don't think so. Unlike the article's author, my work left me feeling model architecture was the most important thing (behind training data) whereas they seem to feel it is ancillary.

[sdenton4]

It's data, then loss, and then, finally, architecture. And including some additional conditioning or metadata to help prediction will often have higher value than an architecture change...

[pictureofabear]

Can you explain this idea a little further? Or do you know of some further reading on this topic?