Software accompanying "NeuralFDR: Learning Discovery Thresholds from Hypothesis Features", NIPS 2017
You will have to install PyTorch to run the code, follow the instructions from http://pytorch.org
Download the data used in the paper from this dropbox folder.
python train.py --data data/data_airway.csv --dim 1 --out airway
The report will be available in airway folder
If you use this code, please cite
@inproceedings{xia2017neuralfdr,
title={NeuralFDR: Learning Discovery Thresholds from Hypothesis Features},
author={Xia, Fei and Zhang, Martin J and Zou, James Y and Tse, David},
booktitle={Advances in Neural Information Processing Systems},
pages={1540--1549},
year={2017}
}