The Spectral Bias of Polynomial Neural Networks
This work addresses the spectral bias problem in neural networks for researchers and practitioners in machine learning, offering incremental insights into architecture design.
The paper tackled the spectral bias of polynomial neural networks (PNNs) by analyzing their Neural Tangent Kernel, finding that the Π-Net family speeds up learning of higher frequencies, which was verified through extensive experiments.
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 $\textit{spectral bias}$ 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 $Π$-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.