paper-with-me

Papers

Scaling Neural Program Synthesis with Distribution-based Search

2021-10-24 · Nathanaël Fijalkow, Guillaume Lagarde, Théo Matricon, Kevin Ellis, Pierre Ohlmann, Akarsh Potta

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.

📄 PDF Abstract BibTeX arXiv:2110.12485

Code (1)

nathanael-fijalkow/deepsynth 공식 구현 pytorch

Tasks

Program Synthesis

Similar Papers 제목 키워드 기반

Beyond the Training Distribution: Mapping Generalization Boundaries in Neural Program Synthesis

2026-04-30 · Henrik Voigt, Michael Habeck, Joachim Giesen arxiv

Large-scale transformers achieve impressive results on program synthesis benchmarks, yet their true generalization capabilities remain obscured by data contamination and opaque training corpora. To rigorously assess whet…

Program Synthesis

Iterative Genetic Improvement: Scaling Stochastic Program Synthesis

2022-02-26 · Yuan Yuan, Wolfgang Banzhaf

Program synthesis aims to {\it automatically} find programs from an underlying programming language that satisfy a given specification. While this has the potential to revolutionize computing, how to search over the vast…

Program Synthesis

Searching Latent Program Spaces

2024-11-13 · Clément Bonnet, Matthew V Macfarlane

Program synthesis methods aim to automatically generate programs restricted to a language that can explain a given specification of input-output pairs. While purely symbolic approaches suffer from a combinatorial search …

ARCProgram inductionProgram SynthesisTest-time Adaptation

Neural Program Synthesis with a Differentiable Fixer

2020-06-19 · Matej Balog, Rishabh Singh, Petros Maniatis, Charles Sutton

We present a new program synthesis approach that combines an encoder-decoder based synthesis architecture with a differentiable program fixer. Our approach is inspired from the fact that human developers seldom get their…

DecoderProgram Synthesis

Optimal Neural Program Synthesis from Multimodal Specifications

2020-10-04 · Findings (EMNLP) 2021 11 · Xi Ye, Qiaochu Chen, Isil Dillig, Greg Durrett

Multimodal program synthesis, which leverages different types of user input to synthesize a desired program, is an attractive way to scale program synthesis to challenging settings; however, it requires integrating noisy…

Program Synthesisvalid