Work

Field Matching: an Electrostatic Paradigm to Generate and Transfer Data

Year: 2025

Type: preprint

Abstract: We propose Electrostatic Field Matching (EFM), a novel method that is suitable for both generative modeling 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. Then we learn the electrostatic field of the capacitor 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. Our code is available at https://github.com/justkolesov/FieldMatching

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2502.02367

Authors: Kolesov, Alexander, Stepan, Manukhov, Palyulin, Vladimir V., Korotin, Alexander

Institutions: Skolkovo Institute of Science and Technology, AIRI - Artificial Intelligence Research Institute

Language: English

Topic: Domain Adaptation and Few-Shot Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: Skolkovo Institute of Science and Technology, Ministero dello Sviluppo Economico

OpenAlex ID: W4407186345

Cites:

Cited by:

Related to: 10