jacob-m-wilson-42

Flux docs missing withgradient() call for multi-objective loss functions

6

After talking with @mcabbott on slack, we determined that Flux is missing documentation for a `withgradient()` call for multi-objective optimization. @mcabbott provided the below code ```julia trio, grads = withgradient(model)...

ReverseDiff documentation shows issue that has been fixed? Nested differentiation of a closure?

1

Hello everyone. The ReverseDiff documentation under "Limitations of ReverseDiff" lists the following **Nested differentiation of closures is dangerous.** Differentiating closures is safe, and nested differentation is safe, but you might...

**Describe the bug** When two cuarrays of different sizes are added together, if the first array is larger than the second array, then no error is thrown and an unknown...