Learning to learn by gradient descent by gradient descent - TF2

Head over to the Wiki on L2O for a more comprehensive view on the paper and my implementation.

• Quadratics
• MNIST

Or to reproduce the graph or something similar, head to the .\revised and follow the instructions in the readme file.

To be implemented:

• Coordinate-Wise optimizer
• GPU Run

Citations

@article{andrychowicz2016learning,
  title={Learning to learn by gradient descent by gradient descent},
  author={Andrychowicz, Marcin and Denil, Misha and Gomez, Sergio and Hoffman, Matthew W and Pfau, David and Schaul, Tom and Shillingford, Brendan and De Freitas, Nando},
  journal={Advances in neural information processing systems},
  volume={29},
  year={2016}
}