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	484	July 16, 2022
Apply hessian of neural network to array Machine Learning	2	413	March 20, 2021
Batched gradients and hessians with Flux Machine Learning question	10	308	January 25, 2025
Errors when trying to compute hessian of flux neural net and jacobian of jacobian with zygote Machine Learning flux , zygote	1	393	July 4, 2022
[Flux] Issue while computing Hessian MethodError: objects of type Tracker.Grads are not callable Machine Learning flux	12	1435	August 28, 2019