= SGD in the PyTorch documentation
{c}
https://docs.pytorch.org/docs/2.15/generated/torch.optim.SGD.html
Pinned PyTorch2.15 primary API documentation. Algorithm pseudocode and lr parameter define the learning-rate-scaled gradient update. The scalar quadratic example sets momentum, weight decay and other modifications to zero; no PyTorch package or native build is run.
Further PyTorch2.15 locators: algorithm pseudocode and the note comparing momentum conventions, including first-buffer initialization and the handling of dampening at the first step.
Back to article page
