Adversarial Fairness and Pytorch crashing

[nyangnicole]

Describe the bug

When I run the AdversarialFairness mitigator with a pytorch backend, the kernel dies, when I run it with 7 or more covariates.
It does not crash when I use a tensor flow backend.

Steps/Code to Reproduce

Sample code to reproduce the problem

Expected Results

No error is thrown.

Actual Results

Kernel dies.

Screenshots

Versions

OS: Mac
Browser: Safari
Python version: 3.9.13
Fairlearn version: 0.8.0
Pytorch version: 2.0.0
Torchvision version: 0.15.1

System:
python: 3.9.13 (main, Aug 25 2022, 18:29:29) [Clang 12.0.0 ]
executable: /Users/nicoleyang/opt/anaconda3/bin/python
machine: macOS-10.16-x86_64-i386-64bit

Python dependencies:
Cython: 0.29.32
matplotlib: 3.5.2
numpy: 1.21.5
pandas: 1.4.4
pip: 22.2.2
scipy: 1.9.1
setuptools: 63.4.1
sklearn: 1.0.2
tempeh: None

[romanlutz]

Can you provide a minimal example that we can use to reproduce the issue?