Skip to Main content Skip to Navigation
Journal articles

Scaling Neural Program Synthesis with Distribution-Based Search

Abstract : We consider the problem of automatically constructing computer programs from input-output examples. We investigate how to augment probabilistic and neural program synthesis methods with new search algorithms, proposing a framework called distribution-based search. Within this framework, we introduce two new search algorithms: Heap Search, an enumerative method, and SQRT Sampling, a probabilistic method. We prove certain optimality guarantees for both methods, show how they integrate with probabilistic and neural techniques, and demonstrate how they can operate at scale across parallel compute environments. Collectively these findings offer theoretical and applied studies of search algorithms for program synthesis that integrate with recent developments in machine-learned program synthesizers.
Document type :
Journal articles
Complete list of metadata

https://hal-cnrs.archives-ouvertes.fr/hal-03775025
Contributor : Nathanaël Fijalkow Connect in order to contact the contributor
Submitted on : Monday, September 12, 2022 - 11:48:05 AM
Last modification on : Monday, September 12, 2022 - 11:48:06 AM

Links full text

Identifiers

Collections

Citation

Nathanaël Fijalkow, Guillaume Lagarde, Théo Matricon, Kevin Ellis, Pierre Ohlmann, et al.. Scaling Neural Program Synthesis with Distribution-Based Search. Proceedings of the AAAI Conference on Artificial Intelligence, 2022, 36 (6), pp.6623-6630. ⟨10.1609/aaai.v36i6.20616⟩. ⟨hal-03775025⟩

Share

Metrics

Record views

0