Machine Learning for Quantifier Selection in cvc5
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F24%3A00380239" target="_blank" >RIV/68407700:21730/24:00380239 - isvavai.cz</a>
Result on the web
<a href="https://doi.org/10.3233/FAIA241009" target="_blank" >https://doi.org/10.3233/FAIA241009</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.3233/FAIA241009" target="_blank" >10.3233/FAIA241009</a>
Alternative languages
Result language
angličtina
Original language name
Machine Learning for Quantifier Selection in cvc5
Original language description
In this work we considerably improve the state-of-the-art SMT solving on first-order quantified problems by efficient machine learning guidance of quantifier selection. Quantifiers represent a sig nificant challenge for SMT and are technically a source of undecid ability. In our approach, we train an efficient machine learning model that informs the solver which quantifiers should be instantiated and which not. Each quantifier may be instantiated multiple times and the set of the active quantifiers changes as the solving progresses. There fore, we invoke the ML predictor many times, during the whole run of the solver. To make this efficient, we use fast ML models based on gradient boosted decision trees. We integrate our approach into the state-of-the-art cvc5 SMT solver and show a considerable increase of the system’s holdout-set performance after training it on a large set of first-order problems collected from the Mizar Mathematical Library.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
Result was created during the realization of more than one project. More information in the Projects tab.
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2024
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
ECAI 2024 - 27th European Conference on Artificial Intelligence
ISBN
978-1-64368-548-9
ISSN
0922-6389
e-ISSN
1879-8314
Number of pages
8
Pages from-to
4336-4343
Publisher name
IOS Press
Place of publication
Oxford
Event location
Santiago de Compostela
Event date
Oct 19, 2024
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—