# Zygote AD Jacobian-vector product

**URL:** <https://discourse.julialang.org/t/zygote-ad-jacobian-vector-product/40857>\
**Category:** Specific Domains\
**Tags:** differentiation, zygote\
**Created:** [June 6, 2020, 10:39am UTC](https://discourse.julialang.org/t/zygote-ad-jacobian-vector-product/40857 "2020-06-06T10:39:00Z")\
**Posts on this page:** 1\
**Showing post:** 4

<div class="post-metadata">

**Author:** ![pavanakumar](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/pavanakumar/32/22096_2.png) [@pavanakumar](https://discourse.julialang.org/u/pavanakumar)\
**Post date:** [June 6, 2020, 1:38pm UTC](https://discourse.julialang.org/t/zygote-ad-jacobian-vector-product/40857/4 "2020-06-06T13:38:16Z")

</div>

The forward mode Jac-vec is described here in the following post

> [@Efficient Vector^T \* Jacobian matrix?](https://discourse.julialang.org/t/efficient-vector-t-jacobian-matrix/21329/2):
>
> This is exactly what reverse-mode automatic differentiation is (e.g. if f is R^n to R you’re asking for a O(1) gradient). There are a few packages doing it, but it’s more tricky than forward diff.

Many thanks for pointing me in the right direction.

---

_[View the full topic](https://discourse.julialang.org/t/zygote-ad-jacobian-vector-product/40857)._