English

Fast Clifford Neural Layers

Machine Learning 2025-07-03 v1 Artificial Intelligence Neural and Evolutionary Computing Performance

Abstract

Clifford Neural Layers improve PDE modeling by introducing Clifford Algebra into neural networks. In this project we focus on optimizing the inference of 2/3D Clifford convolutional layers and multivector activation layers for one core CPU performance. Overall, by testing on a real network block involving Clifford convolutional layers and multivector activation layers, we observe that our implementation is 30% faster than standard PyTorch implementation in relatively large data + network size (>L2 cache). We open source our code base at https://github.com/egretwAlker/c-opt-clifford-layers

Keywords

Cite

@article{arxiv.2507.01040,
  title  = {Fast Clifford Neural Layers},
  author = {Tianxiang Xia and Max Neuwinger and Lin Xiao},
  journal= {arXiv preprint arXiv:2507.01040},
  year   = {2025}
}

Comments

7 pages content-wise

R2 v1 2026-07-01T03:42:06.283Z