I have a function that I want to take the gradient of in the end. I want to achive that a certain variable is deemed independent of the variable i wish to differentiate in the the end. I tried to do this with the Zygote.ignore() function but this does not seem to work: function test(A) Zygote.i…

Taking variable as independent with Zygote (Automatic differentiation)

trahflow February 10, 2022, 12:36pm 2

function test(A)
    B = Zygote.@ignore A
    norm(A * B)
end

Topic		Replies	Views
Ignore part of the gradient calculation inside differential equation model Numerics diffeq , zygote , autodiff , differentialequation	0	316	November 9, 2022
Ignore derivatives in ReverseDiff Machine Learning zygote , reversediff , autodiff , chainrulescore	0	392	April 8, 2023
Reusing variables with Zygote? Specific Domains package , zygote , autodiff	0	68	July 5, 2025
Functionality of torch.nograd General Usage	1	250	January 2, 2023
Zygote: how to get intermediate values without evaluating function twice? General Usage differentiation , zygote	4	774	October 11, 2021