Automatic differentiation with default.tensor, jax and quimb

[RisingPhoelix]

Feature details

Currently, Pennylane's default.tensor only supports parameter shift and Hadamard differentiation methods. However, quimb actually also supports automatic differentiation and is compatible to jax (see here). Is it possible to improve default.tensor to use that natively?

This feature would be super cool and might speed up many large scale variational tasks.

Implementation

No response

How important would you say this feature is?

2: Somewhat important. Needed this quarter.

Additional information

No response

[CatalinaAlbornoz]

Hi @RisingPhoelix , thanks for the suggestion!
Unfortunately our team is currently focused on other core priorities and won't be able to add this enhancement nor review a PR for it at the moment. There's no timeline for when we'll get to it, but we'll leave this issue open for when we eventually have the capacity.