stjordanis / easy-to-hard

Official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks"

Easy-To-Hard

The official repository for the paper "Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks".

Getting Started

Requirements

To install requirements:

pip install -r requirements.txt

To use the datasets we use in this project, we recommend you install our Python package easy-to-hard-data by running:

pip install easy-to-hard-data

You many also download raw datasets. See the Google Drive folder.

Training & Testing

See the dataset specific documentation in the corresonding directories: Prefix Sums, Mazes, Chess.

Citing our paper

If you find this code helpful, please consider citing our work.

@misc{schwarzschild2021learn,
      title={Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks}, 
      author={Avi Schwarzschild and Eitan Borgnia and Arjun Gupta and Furong Huang and Uzi Vishkin and Micah Goldblum and Tom Goldstein},
      year={2021},
      eprint={2106.04537},
      archivePrefix={arXiv},
      primaryClass={cs.LG}
}