Enregistré dans:
Détails bibliographiques
Auteurs principaux: Anupam, Sagnik, Bowers, Maddy, Costilla-Reyes, Omar, Solar-Lezama, Armando
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2409.17490
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910740368064512
author Anupam, Sagnik
Bowers, Maddy
Costilla-Reyes, Omar
Solar-Lezama, Armando
author_facet Anupam, Sagnik
Bowers, Maddy
Costilla-Reyes, Omar
Solar-Lezama, Armando
contents We present MathDSL, a Domain-Specific Language (DSL) for mathematical equation solving, which, when deployed in program synthesis models, outperforms state-of-the-art reinforcement-learning-based methods. We also introduce a quantitative metric for measuring the conciseness of a mathematical solution and demonstrate the improvement in the quality of generated solutions compared to other methods. Our system demonstrates that a program synthesis system (DreamCoder) using MathDSL can generate programs that solve linear equations with greater accuracy and conciseness than using reinforcement learning systems. Additionally, we demonstrate that if we use the action spaces of previous reinforcement learning systems as DSLs, MathDSL outperforms the action-space-DSLs. We use DreamCoder to store equation-solving strategies as learned abstractions in its program library and demonstrate that by using MathDSL, these can be converted into human-interpretable solution strategies that could have applications in mathematical education.
format Preprint
id arxiv_https___arxiv_org_abs_2409_17490
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MathDSL: A Domain-Specific Language for Concise Mathematical Solutions Via Program Synthesis
Anupam, Sagnik
Bowers, Maddy
Costilla-Reyes, Omar
Solar-Lezama, Armando
Machine Learning
We present MathDSL, a Domain-Specific Language (DSL) for mathematical equation solving, which, when deployed in program synthesis models, outperforms state-of-the-art reinforcement-learning-based methods. We also introduce a quantitative metric for measuring the conciseness of a mathematical solution and demonstrate the improvement in the quality of generated solutions compared to other methods. Our system demonstrates that a program synthesis system (DreamCoder) using MathDSL can generate programs that solve linear equations with greater accuracy and conciseness than using reinforcement learning systems. Additionally, we demonstrate that if we use the action spaces of previous reinforcement learning systems as DSLs, MathDSL outperforms the action-space-DSLs. We use DreamCoder to store equation-solving strategies as learned abstractions in its program library and demonstrate that by using MathDSL, these can be converted into human-interpretable solution strategies that could have applications in mathematical education.
title MathDSL: A Domain-Specific Language for Concise Mathematical Solutions Via Program Synthesis
topic Machine Learning
url https://arxiv.org/abs/2409.17490