“you multiply these terms out, when you try to compute the…” — Dwarkesh Podcast at 1:30:37
“you multiply these terms out, when you try to compute the variance of this, and so variance of the gradient is equal to expectation of squared minus, and just for simplicity, we can pretend this is like on average zero or something, if you're centering it at no signal. And the variance here”
0:00
2:37:29