Machine learning BPS spectra and the gap conjecture
- Creators
-
Gukov, Sergei1
-
Seong, Rak-Kyeong2
-
1.
California Institute of Technology
-
2.
Ulsan National Institute of Science and Technology
Abstract
We explore statistical properties of Bogomol'nyi-Prasad-Sommerfield q-series for 3d N=2 strongly coupled supersymmetric theories that correspond to a particular family of three-manifolds Y. We discover that gaps between exponents in the q-series are statistically more significant at the beginning of the q-series compared to gaps that appear in higher powers of q. Our observations are obtained by calculating saliencies of q-series features used as input data for principal component analysis, which is a standard example of an explainable machine learning technique that allows for a direct calculation and a better analysis of feature saliencies. Published by the American Physical Society 2024
Copyright and License
Published by the American Physical Society under the terms of the Creative Commons Attribution 4.0 International license. Further distribution of this work must maintain attribution to the author(s) and the published article’s title, journal citation, and DOI. Funded by SCOAP3.
Acknowledgement
The authors would like to thank Miranda Cheng, Hee-Joong Chung, Shimal Harichurn, Arnav S. Kabra, Davide Passaro, Fabian Ruehle, and Josef Svoboda for discussions and comments. The work of S. G. is supported in part by a Simons Collaboration Grant on New Structures in Low-Dimensional Topology, by the NSF Grant No. DMS-2245099, and by the U.S. Department of Energy, Office of Science, Office of High Energy Physics, under Award No. DE-SC0011632. R.-K. S. is supported by a Basic Research Grant of the National Research Foundation of Korea (NRF-2022R1F1A1073128). He is also supported by a Start-up Research Grant for new faculty at UNIST (1.210139.01) and a UNIST AI Incubator Grant (1.240022.01). He is also partly supported by the BK21 Program (“Next Generation Education Program for Mathematical Sciences,” 4299990414089) funded by the Ministry of Education in Korea and the National Research Foundation of Korea (NRF).
Files
| Name | Size | Download all |
|---|---|---|
|
md5:48c41f0f22768240b90dfb26871b704e
|
868.0 kB | Preview Download |
Additional details
- ISSN
- 2470-0029
- National Science Foundation
- DMS-2245099
- United States Department of Energy
- Office of Science
- Office of High Energy Physics
- DE-SC0011632
- National Research Foundation of Korea
- NRF-2022R1F1A1073128
- Ulsan National Institute of Science and Technology
- 1.210139.01
- Ulsan National Institute of Science and Technology
- 1.240022.01
- Institute of BioMed-IT, Energy-IT and Smart-IT Technology (Best), Yonsei University
- 4299990414089
- Ministry of Education
- Simons Collaboration
- Accepted
-
2024-07-18Accepted
- Publication Status
- Published