Kārlis Freivalds, Emīls Ozoliņš, Guntis Bārzdiņš. Discrete Denoising Diffusion Approach to Integer Factorization. 32nd International Conference on Artificial Neural Networks, 14254(1), 123-134 pp. Lecture Notes in Computer Science (LNCS), 2023.

Bibtex citation:
@inproceedings{15316_2023,
author = {Kārlis Freivalds and Emīls Ozoliņš and Guntis Bārzdiņš},
title = {Discrete Denoising Diffusion Approach to Integer Factorization},
journal = {32nd International Conference on Artificial Neural Networks},
volume = {14254},
issue = {1},
pages = {123-134},
publisher = {Lecture Notes in Computer Science (LNCS)},
year = {2023}
}

Abstract: Integer factorization is a famous computational problem unknown whether being solvable in the polynomial time. With the rise of deep neural networks, it is interesting whether they can facilitate faster factorization. We present an approach to factorization utilizing deep neural networks and discrete denoising diffusion that works by iteratively correcting errors in a partially-correct solution. To this end, we develop a new seq2seq neural network architecture, employ relaxed categorical distribution and adapt the reverse diffusion process to cope better with inaccuracies in the denoising step. The approach is able to find factors for integers of up to 56 bits long. Our analysis indicates that investment in training leads to an exponential decrease of sampling steps required at inference to achieve a given success rate, thus counteracting an exponential run-time increase depending on the bit-length. https://arxiv.org/abs/2309.05295

URL: https://arxiv.org/abs/2309.05295

Quartile: Q3

Scopus search