I’m new to Zygote.jl and I’d like to compute the squared sum of a gradient, i.e., g = gradient(f, x), q = gradient(g’*g, x) Sucessfully did this using Forward mode: function grad_g_sqr(f, d, x) function gs(x) a = ForwardDiff.gradient(f, x) return a' * a / 2 end gg = F…

Compute gradient of gradient norm using zygote

ToucheSir April 20, 2022, 11:48pm 10

1 Like

Topic		Replies	Views
Newbie: Gradient of a gradient performance in Zygote General Usage zygote	2	524	March 21, 2021
Gradient of Gradient in Zygote General Usage	2	2759	January 1, 2021
Different results between Zygote, ForwardDiff, and ReverseDiff New to Julia	11	3480	October 12, 2020
Is it possible perform reverse mode differentiation (Flux.jl with Zygote.jl) of a forward mode differentiation result (e.g. ForwardDiff)? Machine Learning question , flux	3	1465	March 10, 2020
How to use gradient of neural network as the loss function? Machine Learning question	13	2795	March 23, 2021