2021/12/21 by Jun Chen, Chen, Jun, Yuang Liu +7
Mathematics · #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Mathematical Physics (math-ph) #Morphological variations and asymmetry
paper · pdf · doi:10.48550/arxiv.2112.11172
openalex publication_date 2021/12/21 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
In a Riemannian manifold, the Ricci flow is a partial differential equation for evolving the metric to become more regular. We hope that topological structures from such metrics may be used to assist in the tasks of machine learning. However, this part of the work is still missing. In this paper, we propose Ricci flow assisted Eucl2Hyp2Eucl neural networks that bridge this gap between the Ricci flow and deep neural networks by mapping neural manifolds from the Euclidean space to the dynamically stable Poincaré ball and then back to the Euclidean space. As a result, we prove that, if initial metrics have an L2-norm perturbation which deviates from the Hyperbolic metric on the Poincaré ball, the scaled Ricci-DeTurck flow of such metrics smoothly and exponentially converges to the Hyperbolic metric. Specifically, the role of the Ricci flow is to serve as naturally evolving to the stable Poincaré ball. For such dynamically stable neural manifolds under the Ricci flow, the convergence of neural networks embedded with such manifolds is not susceptible to perturbations. And we show that Ricci flow assisted Eucl2Hyp2Eucl neural networks outperform with their all Euclidean counterparts on image classification tasks.