Scaling Neural Program Synthesis with Distribution-Based Search - Archive ouverte HAL Access content directly
Journal Articles Proceedings of the AAAI Conference on Artificial Intelligence Year : 2022

Scaling Neural Program Synthesis with Distribution-Based Search

(1) , , , , ,
1
Guillaume Lagarde
  • Function : Author
Théo Matricon
  • Function : Author
Kevin Ellis
  • Function : Author
Pierre Ohlmann
  • Function : Author
Akarsh Nayan Potta
  • Function : Author

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.

Dates and versions

hal-03775025 , version 1 (12-09-2022)

Identifiers

Cite

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⟩

Collections

CNRS
4 View
0 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More