# Is the SGD in Pytorch a real SGD?

**URL:** <https://discuss.pytorch.org/t/is-the-sgd-in-pytorch-a-real-sgd/9714>\
**Category:** Uncategorized\
**Created:** [November 9, 2017, 12:31pm UTC](https://discuss.pytorch.org/t/is-the-sgd-in-pytorch-a-real-sgd/9714 "2017-11-09T12:31:53Z")\
**Posts on this page:** 1\
**Showing post:** 9

<div class="post-metadata">

**Author:** ![ghlai9665](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/ghlai9665/32/31655_2.png) [@ghlai9665](https://discuss.pytorch.org/u/ghlai9665)\
**Post date:** [November 28, 2020, 4:00pm UTC](https://discuss.pytorch.org/t/is-the-sgd-in-pytorch-a-real-sgd/9714/9 "2020-11-28T16:00:06Z")

</div>

Yeah - newcomer to PyTorch here and I find the SGD name really confusing too. I understand SGD as gradient descent with a batch size of 1, but in reality the batch size is determined by the user. So I agree that it would be much less confusing if it was named just GD because that’s what it is.

---

_[View the full topic](https://discuss.pytorch.org/t/is-the-sgd-in-pytorch-a-real-sgd/9714)._