Tensor Gauge Flow Models
Machine Learning
2025-11-25 v1 Artificial Intelligence
Differential Geometry
Abstract
This paper introduces Tensor Gauge Flow Models, a new class of Generative Flow Models that generalize Gauge Flow Models and Higher Gauge Flow Models by incorporating higher-order Tensor Gauge Fields into the Flow Equation. This extension allows the model to encode richer geometric and gauge-theoretic structure in the data, leading to more expressive flow dynamics. Experiments on Gaussian mixture models show that Tensor Gauge Flow Models achieve improved generative performance compared to both standard and gauge flow baselines.
Keywords
Cite
@article{arxiv.2511.17616,
title = {Tensor Gauge Flow Models},
author = {Alexander Strunk and Roland Assam},
journal= {arXiv preprint arXiv:2511.17616},
year = {2025}
}