# Mini-batch gradient and Loss.backward()

**URL:** <https://discuss.pytorch.org/t/mini-batch-gradient-and-loss-backward/85509>\
**Category:** autograd\
**Created:** [June 15, 2020, 11:03am UTC](https://discuss.pytorch.org/t/mini-batch-gradient-and-loss-backward/85509 "2020-06-15T11:03:52Z")\
**Posts on this page:** 1\
**Showing post:** 2

<div class="post-metadata">

**Author:** ![albanD](https://discuss.pytorch.org/user_avatar/discuss.pytorch.org/alband/32/215_2.png) [@albanD](https://discuss.pytorch.org/u/albanD)\
**Post date:** [June 15, 2020, 2:19pm UTC](https://discuss.pytorch.org/t/mini-batch-gradient-and-loss-backward/85509/2 "2020-06-15T14:19:39Z")

</div>

Duplicate question. Answered there: [Is Loss.backward() function calculate gradients over mini-batch](https://discuss.pytorch.org/t/is-loss-backward-function-calculate-gradients-over-mini-batch/66873/5)

---

_[View the full topic](https://discuss.pytorch.org/t/mini-batch-gradient-and-loss-backward/85509)._