# Backpropagation with lightning.qubit and PyTorch **URL:** \ **Category:** PennyLane Help\ **Created:** [February 5, 2022, 5:06pm UTC](https://discuss.pennylane.ai/t/backpropagation-with-lightning-qubit-and-pytorch/1650 "2022-02-05T17:06:15Z")\ **Posts on this page:** 1\ **Showing post:** 2
**Author:** ![josh](https://yyz2.discourse-cdn.com/flex012/user_avatar/discuss.pennylane.ai/josh/32/100_2.png) [@josh](https://discuss.pennylane.ai/u/josh)\ **Post date:** [February 7, 2022, 7:25am UTC](https://discuss.pennylane.ai/t/backpropagation-with-lightning-qubit-and-pytorch/1650/2 "2022-02-07T07:25:35Z")
Hi @karolishp — a very well-founded question! Everything you note is correct: - `backprop` definitely has an overhead on the forward pass, since every intermediate stage of the computation is being stored in memory, to be accumulated later during the backwards pass. - The `adjoint` method is a version of backprop that is designed for unitary/reversible computation — as a result, we are able to remove the memory caching requirements, and replace it with some additional computation. In effect, we are trading a reduction in memory for an increase in computational time, however, this allows us to scale up the regimes where we can use adjoint beyond standard backprop, to ~30 qubits or more. - `parameter-shift` will have the _fastest_ forward execution time (since there is no ‘bookkeeping’ that must be done on the forward pass), but requires 2P separate circuit evaluations on the backwards pass, for all P parameters in the circuit. So useful for small circuits with few parameters, but rapidly becomes unscalable as the number of parameters/qubits increase. > Following [Backpropagation with Pytorch](http://discuss.pennylane.ai/t/backpropagation-with-pytorch/805/2), I tried `lightning.qubit` with `adjoint` , however there are some operations I use that are not supported by adjoint, so that’s not a valid option for my use case. Which operations/measurements do you currently need which aren’t supported with adjoint yet? This will help us build up the adjoint to ensure feature parity. > P.S. I also noticed that using `default.qubit` with `backprop` on PyTorch (as well as `default.qubit.torch` ) gives the following warning message: Would you be able to post: - A small QNode example that generates this warning? - Your Torch, PennyLane, and NumPy versions? This will help us track down the issue 🙂 --- _[View the full topic](https://discuss.pennylane.ai/t/backpropagation-with-lightning-qubit-and-pytorch/1650)._