Flux.jacobian(::Chain, ::AbstractArray) gives the full jacobian of a neural network. Flux.hessian however throws the error “output is not scalar”. Let m = Chain(Dense(5,3,elu), Dense(3,3)) . What I can do is compute the gradient of each value in the jacobian matrix w.r. to each input using Flux.gra…

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

ChrisRackauckas August 2, 2019, 3:04pm 5

That will stack overflow an issue in flux (pun intended)

Topic		Replies	Views
Hessian matrix of a neural network vetor output Specific Domains physics , zygote , neural-network	3	452	July 16, 2022
[Flux] Issue while computing Hessian MethodError: objects of type Tracker.Grads are not callable Machine Learning flux	12	1386	August 28, 2019
Apply hessian of neural network to array Machine Learning	2	395	March 20, 2021
Higher order derivatives in Flux Machine Learning differentiation	3	2434	May 22, 2018
How to compute hessian Machine Learning	1	873	August 26, 2019