←back to thread

Backpropagation is a leaky abstraction (2016)

(karpathy.medium.com)
346 points swatson741 | 1 comments | 02 Nov 25 05:20 UTC | HN request time: 0.363s | source
Show context
drivebyhooting ◴[02 Nov 25 07:21 UTC] No.45788473[source]▶
I have a naive question about backprop and optimizers.

I understand how SGD is just taking a step proportional to the gradient and how backprop computes the partial derivative of the loss function with respect to each model weight.

But with more advanced optimizers the gradient is not really used directly. It gets per weight normalization, fudged with momentum, clipped, etc.

So really, how important is computing the exact gradient using calculus, vs just knowing the general direction to step? Would that be cheaper to calculate than full derivatives?

replies(11): >>45788484 #>>45788525 #>>45788559 #>>45788604 #>>45789234 #>>45789345 #>>45789485 #>>45792574 #>>45792998 #>>45796071 #>>45799773 #
1. HarHarVeryFunny ◴[02 Nov 25 19:04 UTC] No.45792574[source]▶
You don't need exact gradients, since gradient descent is self-correcting (which can make it hard to find gradient calculation bugs!). One approach using inexact gradients is to use predicted "synthetic gradients" which avoids needing to wait for backward pass for weight updates.