%0 Conference Paper %B ICLR 2019 %D 2019 %T Data for free: Fewer-shot algorithm learning with parametricity data augmentation %A Owen Lewis %A Katherine Hermann %X

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.

%B ICLR 2019 %8 04/2019 %G eng