pytorch - connection between loss.backward() and optimizer.step()

Question

Where is an explicit connection between the optimizer and the loss?

How does the optimizer know where to get the gradients of the loss wit

Answer 1

When you call loss.backward(), all it does is compute gradient of loss w.r.t all the parameters in loss that have requires_grad = True and store them in parameter.grad attribute for every parameter.

optimizer.step() updates all the parameters based on parameter.grad