George Stepaniants

Question on how to batch over both: inputs and tangent vectors

3

I want to compute the jacobian vector product of a function F from R^d to R^D. But I need to do this at a batch of points x_1, ..., x_n...

Cannot create zero polynomial

2

I have a very surprising problem, it is impossible to create a Multivariate Polynomial that is constantly zero. This code crashes on my computer: ```julia using MultivariatePolynomials using TypedPolynomials @polyvar...

Move every paragraph after the first one on the training reference page to an info box and preface it for those migrating from earlier versions of Flux.

Question about different adjoint methods

3

Just wanted to ask if I have the right understanding of what algorithms are being used for each adjoint method, as the documentation does not link each method to a...

Adding Support for Lazy Linear Layers

1

Just wanted to ask if at any point, there is consideration to add support for Lazy Linear layers like in PyTorch: https://pytorch.org/docs/stable/generated/torch.nn.LazyLinear.html This is a really useful feature, especially for...

Jitting Callback Function

7

I have a question concerning speeding up my callback function which plots several solutions to a neural ODE. Because evaluating the neural ODE model takes a bit of time (and...