Hi all, I’m quite new (on and off) to Julia and I’m trying to play more consistently with it. I have an issue with AD : I can compute the gradient with respect to the weights of a very simple neural network with Zygote but it fails with Enzyme. I do not have the same problem when I compute the grad…

Lux, ComponentArrays and flat parameters : computing the gradient works with Zygote but not with Enzyme

wsmoses August 6, 2023, 11:11pm 4

The theta Unicode symbol seems to have two different glyfps in the snippet (sorry I made my response on my phone). Can you just write theta in ascii instead of Unicode just to confirm.

Topic		Replies	Views
Zygote much slower than JAX for automatic differentiation of energy Machine Learning performance , flux , zygote , jax , lux	22	1712	May 15, 2024
Lux + Enzyme and Zygote + NeuralODE, segmentation fault Machine Learning machine-learning , differentialequation , enzyme , lux	6	370	March 3, 2025
What's the state of Automatic Differentiation in Julia January 2023? General Usage autodiff	41	12759	June 21, 2024
How to use Lux with Enzyme Machine Learning question	6	714	December 11, 2024
`Zygote.gradient` is 54000 TIMES slower than `jax.gradient` Optimization (Mathematical) zygote , jax	80	1859	February 1, 2025

Lux, ComponentArrays and flat parameters : computing the gradient works with Zygote but not with Enzyme

Related topics