Fabio Peruzzo

Make differentiating inputs optional

2

Hello, I am calculating the EK-FAC representation on the linear layers of a model with an embedding layer. The inputs are integers which are lookup values and therefore should not...

In the notebooks, all the torch models are trained in a sloppy way, e.g. without a proper stopping criterion apart for number of steps. This was to show that influences...

Cache with running average - possible bias and instability

2

Our cache uses a running average to speed up the calculation of the shapley values for non-deterministic training. However, it is unclear how stable montecarlo shapley is towards non-deterministic training,...

### System Info ```Shell - `lerobot` version: 0.1.0 - Platform: macOS-14.7.1-arm64-arm-64bit - Python version: 3.10.15 - Huggingface_hub version: 0.26.2 - Dataset version: 3.1.0 - Numpy version: 1.26.4 - PyTorch version...