Field Matching: An Electrostatic Paradigm to Generate and Transfer Data
Abstract
We propose Electrostatic Field Matching (EFM), a novel method that is suitable for both generative modelling and distribution transfer tasks. Our approach is inspired by the physics of an electrical capacitor. We place source and target distributions on the capacitor plates and assign them positive and negative charges, respectively. We then learn the capacitor’s electrostatic field using a neural network approximator. To map the distributions to each other, we start at one plate of the capacitor and move the samples along the learned electrostatic field lines until they reach the other plate. We theoretically justify that this approach provably yields the distribution transfer. In practice, we demonstrate the performance of our EFM in toy and image data experiments.
Cite
Text
Kolesov et al. "Field Matching: An Electrostatic Paradigm to Generate and Transfer Data." Proceedings of the 42nd International Conference on Machine Learning, 2025.Markdown
[Kolesov et al. "Field Matching: An Electrostatic Paradigm to Generate and Transfer Data." Proceedings of the 42nd International Conference on Machine Learning, 2025.](https://mlanthology.org/icml/2025/kolesov2025icml-field/)BibTeX
@inproceedings{kolesov2025icml-field,
title = {{Field Matching: An Electrostatic Paradigm to Generate and Transfer Data}},
author = {Kolesov, Alexander and Manukhov, S. I. and Palyulin, Vladimir Vladimirovich and Korotin, Alexander},
booktitle = {Proceedings of the 42nd International Conference on Machine Learning},
year = {2025},
pages = {31202-31222},
volume = {267},
url = {https://mlanthology.org/icml/2025/kolesov2025icml-field/}
}