The Spectral Bias of Polynomial Neural Networks
Moulik Choraria, Leello Tadesse Dadi, Grigorios Chrysos, Julien Mairal, Volkan Cevher
Abstract
Polynomial neural networks (PNNs) have been recently shown to be particularly effective at image generation and face recognition, where high-frequency information is critical. Previous studies have revealed that neural networks demonstrate a $\text{\it{spectral bias}}$ towards low-frequency functions, which yields faster learning of low-frequency components during training. Inspired by such studies, we conduct a spectral analysis of the Neural Tangent Kernel (NTK) of PNNs. We find that the $\Pi$-Net family, i.e., a recently proposed parametrization of PNNs, speeds up the learning of the higher frequencies. We verify the theoretical bias through extensive experiments. We expect our analysis to provide novel insights into designing architectures and learning frameworks by incorporating multiplicative interactions via polynomials.
BibTeX
@inproceedings{
choraria2022the,
title={The Spectral Bias of Polynomial Neural Networks},
author={Moulik Choraria and Leello Tadesse Dadi and Grigorios Chrysos and Julien Mairal and Volkan Cevher},
booktitle={International Conference on Learning Representations},
year={2022},
url={https://openreview.net/forum?id=P7FLfMLTSEX}
}