Data for Free: Fewer-Shot Algorithm Learning with Parametricity Data Augmentation
Abstract
We address the problem of teaching an RNN to approximate list-processing algorithms given a small number of input-output training examples. Our approach is to generalize the idea of parametricity from programming language theory to formulate a semantic property that distinguishes common algorithms from arbitrary non-algorithmic functions. This characterization leads naturally to a learned data augmentation scheme that encourages RNNs to learn algorithmic behavior and enables small-sample learning in a variety of list-processing tasks.
Cite
Text
Lewis and Hermann. "Data for Free: Fewer-Shot Algorithm Learning with Parametricity Data Augmentation." ICLR 2019 Workshops: LLD, 2019.Markdown
[Lewis and Hermann. "Data for Free: Fewer-Shot Algorithm Learning with Parametricity Data Augmentation." ICLR 2019 Workshops: LLD, 2019.](https://mlanthology.org/iclrw/2019/lewis2019iclrw-data/)BibTeX
@inproceedings{lewis2019iclrw-data,
title = {{Data for Free: Fewer-Shot Algorithm Learning with Parametricity Data Augmentation}},
author = {Lewis, Owen and Hermann, Katherine},
booktitle = {ICLR 2019 Workshops: LLD},
year = {2019},
url = {https://mlanthology.org/iclrw/2019/lewis2019iclrw-data/}
}