Karlis Freivalds, Sergejs Kozlovičs. Denoising Diffusion for Sampling SAT Solutions. NeurIPS 2022 Workshop on Score-Based Methods, 2022.
Bibtex citation:
Bibtex citation:
@inproceedings{13054_2022,
author = {Karlis Freivalds and Sergejs Kozlovičs},
title = {Denoising Diffusion for Sampling SAT Solutions},
journal = {NeurIPS 2022 Workshop on Score-Based Methods},
year = {2022}
}
author = {Karlis Freivalds and Sergejs Kozlovičs},
title = {Denoising Diffusion for Sampling SAT Solutions},
journal = {NeurIPS 2022 Workshop on Score-Based Methods},
year = {2022}
}
Abstract: Generating diverse solutions to the Boolean Satisfiability Problem (SAT) is a hard computational problem with practical applications for testing and functional verification of software and hardware designs. We explore the way to generate such solutions using Denoising Diffusion coupled with a Graph Neural Network to implement the denoising function. We find that the obtained accuracy is similar to the currently best purely neural method and the produced SAT solutions are highly diverse, even if the system is trained with non-random solutions from a standard solver.