# Is there an efficient way to compute the Hessian of a NN?

**URL:** https://discourse.julialang.org/t/is-there-an-efficient-way-to-compute-the-hessian-of-a-nn/26971
**Category:** Machine Learning
**Tags:** flux
**Created:** [July 30, 2019, 10:08am UTC](https://discourse.julialang.org/t/is-there-an-efficient-way-to-compute-the-hessian-of-a-nn/26971 "2019-07-30T10:08:33Z")
**Posts on this page:** 1
**Showing post:** 3

<div class="post-metadata">

### Author: ![ChrisRackauckas](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/chrisrackauckas/32/77_2.png) [@ChrisRackauckas](https://discourse.julialang.org/u/ChrisRackauckas)
#### Post date: [July 30, 2019, 4:24pm UTC](https://discourse.julialang.org/t/is-there-an-efficient-way-to-compute-the-hessian-of-a-nn/26971/3 "2019-07-30T16:24:48Z")

</div>

Reverse mode is going to give columns, and I don’t think you need that. Using double forward mode will be the fastest here. You’ll need to `mapchildren` to remove the tracker information (or use the `Flux#zygote` branch) and then just forward diff (or use a hyperdual)

If you do want to Forward-over-Reverse for Hess-vec products though, it is implemented in SparseDiffTools.jl

[https://github.com/JuliaDiffEq/SparseDiffTools.jl#jacobian-vector-and-hessian-vector-products](https://github.com/JuliaDiffEq/SparseDiffTools.jl#jacobian-vector-and-hessian-vector-products)

but note that our tests don’t show that using Zygote here is the fastest yet 🤷‍♂️

---

_[View the full topic](https://discourse.julialang.org/t/is-there-an-efficient-way-to-compute-the-hessian-of-a-nn/26971)._