JuliaSmoothOptimizers / JuliaSmoothOptimizers/FluxNLPModels.jl
Implement hessian functions with different minibatch
Open
- Dominant language
- Julia
- Stars
- 7
- Forks
- 4
- PR merge metrics
- No merged PRs in 30d
Description
As I mentioned in [Zulip](https://optimizers.zulipchat.com/#narrow/channel/297165-general/topic/FluxNLPModels.2Ejl/near/480757460),
I would like to use `FluxNLPModels.jl` and I need to use second order information. According to `Flux.jl`, one can use again `gradient` to compute the hessian.
In fact, I want a possible different batch to compute the hessian in relation to the gradient.
I saw the in `FluxNLPModels.jl` the NLPModels functions `grad` and `objgrad` are implemented.
* Should we implement the functions related to the hessian?
* If so, use of Zygote (as Flux.jl indicates) is preferable?
Contributor guide
Assessment
This issue has not been assessed yet.