Learning Libraries of Subroutines for Neurally–Guided Bayesian Program Induction



Published on




Successful approaches to program induction require a hand-engineered domainspecific language (DSL), constraining the space of allowed programs and imparting prior knowledge of the domain. We contribute a program induction algorithm called EC2 that learns a DSL while jointly training a neural network to efficiently search for programs in the learned DSL. We use our model to synthesize functions on lists, edit text, and solve symbolic regression problems, showing how the model learns a domain-specific library of program components for expressing solutions to problems in the domain.

Please cite our work using the BibTeX below.

 author = {Ellis, Kevin and Morales, Lucas and Sabl\'{e}-Meyer, Mathias and Solar-Lezama, Armando and Tenenbaum, Josh},
 booktitle = {Advances in Neural Information Processing Systems},
 editor = {S. Bengio and H. Wallach and H. Larochelle and K. Grauman and N. Cesa-Bianchi and R. Garnett},
 pages = {},
 publisher = {Curran Associates, Inc.},
 title = {Learning Libraries of Subroutines for Neurally\textendash Guided Bayesian Program Induction},
 url = {},
 volume = {31},
 year = {2018}
Close Modal