Interaction Field Matching: Overcoming Limitations of Electrostatic Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915829354856448 |
|---|---|
| author | Manukhov, Stepan I. Kolesov, Alexander Palyulin, Vladimir V. Korotin, Alexander |
| author_facet | Manukhov, Stepan I. Kolesov, Alexander Palyulin, Vladimir V. Korotin, Alexander |
| contents | Electrostatic field matching (EFM) has recently appeared as a novel physics-inspired paradigm for data generation and transfer using the idea of an electric capacitor. However, it requires modeling electrostatic fields using neural networks, which is non-trivial because of the necessity to take into account the complex field outside the capacitor plates. In this paper, we propose Interaction Field Matching (IFM), a generalization of EFM which allows using general interaction fields beyond the electrostatic one. Furthermore, inspired by strong interactions between quarks and antiquarks in physics, we design a particular interaction field realization which solves the problems which arise when modeling electrostatic fields in EFM. We show the performance on a series of toy and image data transfer problems. Our code is available at https://github.com/justkolesov/InteractionFieldMatching |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_02950 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Interaction Field Matching: Overcoming Limitations of Electrostatic Models Manukhov, Stepan I. Kolesov, Alexander Palyulin, Vladimir V. Korotin, Alexander Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition Electrostatic field matching (EFM) has recently appeared as a novel physics-inspired paradigm for data generation and transfer using the idea of an electric capacitor. However, it requires modeling electrostatic fields using neural networks, which is non-trivial because of the necessity to take into account the complex field outside the capacitor plates. In this paper, we propose Interaction Field Matching (IFM), a generalization of EFM which allows using general interaction fields beyond the electrostatic one. Furthermore, inspired by strong interactions between quarks and antiquarks in physics, we design a particular interaction field realization which solves the problems which arise when modeling electrostatic fields in EFM. We show the performance on a series of toy and image data transfer problems. Our code is available at https://github.com/justkolesov/InteractionFieldMatching |
| title | Interaction Field Matching: Overcoming Limitations of Electrostatic Models |
| topic | Machine Learning Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.02950 |