Update – using latest Flux. I’d like to optimize a function of the singular values of a matrix. The Flux training loop barfs. Here’s my code using Flux, ForwardDiff, LinearAlgebra, GenericLinearAlgebra m = 20 X = randn(m,m) model = Dense(m,m) loss(X) = sum(GenericLinearAlgebra.svdvals(model(X))) …

Here’s how you can get the gradient working: using Flux, Zygote, ForwardDiff using GenericLinearAlgebra: svdvals svdvals2(X) = Zygote.forwarddiff(svdvals, X) m = 20 X = randn(m,m) model = Dense(m,m) loss(X) = sum(svdvals2(X)) ## nuclear norm loss(X) gradient(loss, X) This plugs in forwarddiff …

Using Flux to optimize a function of the Singular Values

Specific Domains Optimization (Mathematical)

baggepinnen May 18, 2020, 10:57am 2

Welcome to this forum! See this post

to make the code more readable

2 Likes

Topic		Replies	Views
Help with gradient Machine Learning flux	6	1193	January 31, 2020
Julia method error Machine Learning	6	485	May 18, 2020
Very basic Flux problem Machine Learning	1	1546	June 25, 2019
Another error with defining Flux.jl gradients Machine Learning first-steps , flux	5	1663	December 5, 2018
Error optimizing using autodifferentation General Usage package , differentiation , optimization	7	1073	April 23, 2020

Using Flux to optimize a function of the Singular Values

Related topics