English

Higher Gauge Flow Models

Artificial Intelligence 2026-03-04 v3 Machine Learning Differential Geometry

Abstract

This paper introduces Higher Gauge Flow Models, a novel class of Generative Flow Models. Building upon ordinary Gauge Flow Models (arXiv:2507.13414), these Higher Gauge Flow Models leverage an L_{\infty}-algebra, effectively extending the Lie Algebra. This expansion allows for the integration of the higher geometry and higher symmetries associated with higher groups into the framework of Generative Flow Models. Experimental evaluation on a Gaussian Mixture Model dataset revealed substantial performance improvements compared to traditional Flow Models.

Keywords

Cite

@article{arxiv.2507.16334,
  title  = {Higher Gauge Flow Models},
  author = {Alexander Strunk and Roland Assam},
  journal= {arXiv preprint arXiv:2507.16334},
  year   = {2026}
}

Comments

arXiv admin note: text overlap with arXiv:2507.13414

R2 v1 2026-07-01T04:12:55.415Z