Score: 1

Fiber Bundle Networks: A Geometric Machine Learning Paradigm

Published: December 1, 2025 | arXiv ID: 2512.01151v1

By: Dong Liu

BigTech Affiliations: Massachusetts Institute of Technology

Potential Business Impact:

Makes AI understand things by seeing patterns.

Business Areas:
Intelligent Systems Artificial Intelligence, Data and Analytics, Science and Engineering

We propose Fiber Bundle Networks (FiberNet), a novel machine learning framework integrating differential geometry with machine learning. Unlike traditional deep neural networks relying on black-box function fitting, we reformulate classification as interpretable geometric optimization on fiber bundles, where categories form the base space and wavelet-transformed features lie in the fibers above each category. We introduce two innovations: (1) learnable Riemannian metrics identifying important frequency feature components, (2) variational prototype optimization through energy function minimization. Classification is performed via Voronoi tessellation under the learned Riemannian metric, where each prototype defines a decision region and test samples are assigned to the nearest prototype, providing clear geometric interpretability. This work demonstrates that the integration of fiber bundle with machine learning provides interpretability and efficiency, which are difficult to obtain simultaneously in conventional deep learning.

Country of Origin
🇺🇸 United States

Page Count
18 pages

Category
Computer Science:
Machine Learning (CS)