[amelius]

I think the point is that with conventional equations we can make increasingly better approximations by just using pen and paper, while with these ML methods, you need to train your system ab initio if you want to improve your approximations.

[optimalsolver]

You can iterate and refine a symbolic regression model to get better and better predictions. You certainly don't need to start from scratch.

[potatoman22]

I don't think one option is inherently better or worse than the other