Jacobian-Free Backprop
Associated Publication
JFB: Jacobian-Free Backpropagation for Implicit Models (arXiv Link)
@article{WuFung2022JFB,
title={JFB: Jacobian-Free Backpropagation for Implicit Models},
author={Fung, Samy Wu and Heaton, Howard and Li, Qiuwei and McKenzie, Daniel and Osher, Stanley and Yin, Wotao},
journal={Proceedings of the AAAI Conference on Artificial Intelligence},
year={2022}
}
Set-up
Install all the requirements:
pip install -r requirements.txt
Training
For each dataset, there are three types of training drivers:
- FPN with our proposed backprop:
python train_CIFAR10.py
python train_CIFAR10_Unaugmented.py
python train_MNIST.py
python train_SVHN.py
- FPN with Jacobian-based backprop:
python train_CIFAR10_Jacobian_Based.py
python train_CIFAR10_Unaugmented_Jacobian_Based.py
python train_MNIST_Jacobian_Based.py
python train_SVHN_Jacobian_Based.py
- Explicit models.
python train_CIFAR10_Explicit.py
python train_CIFAR10_Unaugmented_Explicit.py
python train_MNIST_Explicit.py
python train_SVHN_Explicit.py