English

On the Study of Sample Complexity for Polynomial Neural Networks

Machine Learning 2022-09-07 v2 Machine Learning

Abstract

As a general type of machine learning approach, artificial neural networks have established state-of-art benchmarks in many pattern recognition and data analysis tasks. Among various kinds of neural networks architectures, polynomial neural networks (PNNs) have been recently shown to be analyzable by spectrum analysis via neural tangent kernel, and particularly effective at image generation and face recognition. However, acquiring theoretical insight into the computation and sample complexity of PNNs remains an open problem. In this paper, we extend the analysis in previous literature to PNNs and obtain novel results on sample complexity of PNNs, which provides some insights in explaining the generalization ability of PNNs.

Keywords

Cite

@article{arxiv.2207.08896,
  title  = {On the Study of Sample Complexity for Polynomial Neural Networks},
  author = {Chao Pan and Chuanyi Zhang},
  journal= {arXiv preprint arXiv:2207.08896},
  year   = {2022}
}

Comments

Update references

R2 v1 2026-06-25T01:01:51.917Z