Parameter Setting in SAT Solver using Machine Learning Techniques

Filip Beskyd, Pavel Surynek

2022

Abstract

Boolean satisfiability (SAT) solvers are essential tools for many domains in computer science and engineering. Modern complete search-based SAT solvers represent a universal problem solving tool which often provide higher efficiency than ad-hoc direct solving approaches. Over the course of at least two decades of SAT related research, many variable and value selection heuristics were devised. Heuristics can usually be tuned by single or multiple numerical parameters prior to executing the search process over the concrete SAT instance. In this paper we present a machine learning approach that predicts the parameters of heuristic from the underlying structure of the input SAT instance.

Paper Citation

in Harvard Style

Beskyd F. and Surynek P. (2022). Parameter Setting in SAT Solver using Machine Learning Techniques. In Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-547-0, pages 586-597. DOI: 10.5220/0010910200003116

in Bibtex Style

@conference{icaart22,
author={Filip Beskyd and Pavel Surynek},
title={Parameter Setting in SAT Solver using Machine Learning Techniques},
booktitle={Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2022},
pages={586-597},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010910200003116},
isbn={978-989-758-547-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Parameter Setting in SAT Solver using Machine Learning Techniques
SN - 978-989-758-547-0
AU - Beskyd F.
AU - Surynek P.
PY - 2022
SP - 586
EP - 597
DO - 10.5220/0010910200003116