Spectral Bias in Practice: The Role of Function Frequency in Generalization

• URL: http://arxiv.org/abs/2110.02424v1
• Date: Wed, 6 Oct 2021 00:16:10 GMT
• Title: Spectral Bias in Practice: The Role of Function Frequency in Generalization
• Authors: Sara Fridovich-Keil, Raphael Gontijo-Lopes, Rebecca Roelofs
• Abstract summary: We propose methodologies for measuring spectral bias in modern image classification networks. We find that networks that generalize well strike a balance between having enough complexity to fit the data while being simple enough to avoid overfitting. Our work enables measuring and ultimately controlling the spectral behavior of neural networks used for image classification.
• Score: 10.7218588164913
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite their ability to represent highly expressive functions, deep learning models trained with SGD seem to find simple, constrained solutions that generalize surprisingly well. Spectral bias - the tendency of neural networks to prioritize learning low frequency functions - is one possible explanation for this phenomenon, but so far spectral bias has only been observed in theoretical models and simplified experiments. In this work, we propose methodologies for measuring spectral bias in modern image classification networks. We find that these networks indeed exhibit spectral bias, and that networks that generalize well strike a balance between having enough complexity(i.e. high frequencies) to fit the data while being simple enough to avoid overfitting. For example, we experimentally show that larger models learn high frequencies faster than smaller ones, but many forms of regularization, both explicit and implicit, amplify spectral bias and delay the learning of high frequencies. We also explore the connections between function frequency and image frequency and find that spectral bias is sensitive to the low frequencies prevalent in natural images. Our work enables measuring and ultimately controlling the spectral behavior of neural networks used for image classification, and is a step towards understanding why deep models generalize well

Related papers

• Tuning Frequency Bias of State Space Models [48.60241978021799]
  State space models (SSMs) leverage linear, time-invariant (LTI) systems to learn sequences with long-range dependencies. We find that SSMs exhibit an implicit bias toward capturing low-frequency components more effectively than high-frequency ones.
  arXiv  Detail & Related papers  (2024-10-02T21:04:22Z)
• GrassNet: State Space Model Meets Graph Neural Network [57.62885438406724]
  Graph State Space Network (GrassNet) is a novel graph neural network with theoretical support that provides a simple yet effective scheme for designing arbitrary graph spectral filters. To the best of our knowledge, our work is the first to employ SSMs for the design of graph GNN spectral filters. Extensive experiments on nine public benchmarks reveal that GrassNet achieves superior performance in real-world graph modeling tasks.
  arXiv  Detail & Related papers  (2024-08-16T07:33:58Z)
• A Scalable Walsh-Hadamard Regularizer to Overcome the Low-degree Spectral Bias of Neural Networks [79.28094304325116]
  Despite the capacity of neural nets to learn arbitrary functions, models trained through gradient descent often exhibit a bias towards simpler'' functions. We show how this spectral bias towards low-degree frequencies can in fact hurt the neural network's generalization on real-world datasets. We propose a new scalable functional regularization scheme that aids the neural network to learn higher degree frequencies.
  arXiv  Detail & Related papers  (2023-05-16T20:06:01Z)
• Understanding the Spectral Bias of Coordinate Based MLPs Via Training Dynamics [2.9443230571766854]
  We study the connection between the computations of ReLU networks, and the speed of gradient descent convergence. We then use this formulation to study the severity of spectral bias in low dimensional settings, and how positional encoding overcomes this.
  arXiv  Detail & Related papers  (2023-01-14T04:21:25Z)
• Neural networks trained with SGD learn distributions of increasing complexity [78.30235086565388]
  We show that neural networks trained using gradient descent initially classify their inputs using lower-order input statistics. We then exploit higher-order statistics only later during training. We discuss the relation of DSB to other simplicity biases and consider its implications for the principle of universality in learning.
  arXiv  Detail & Related papers  (2022-11-21T15:27:22Z)
• Momentum Diminishes the Effect of Spectral Bias in Physics-Informed Neural Networks [72.09574528342732]
  Physics-informed neural network (PINN) algorithms have shown promising results in solving a wide range of problems involving partial differential equations (PDEs) They often fail to converge to desirable solutions when the target function contains high-frequency features, due to a phenomenon known as spectral bias. In the present work, we exploit neural tangent kernels (NTKs) to investigate the training dynamics of PINNs evolving under gradient descent with momentum (SGDM)
  arXiv  Detail & Related papers  (2022-06-29T19:03:10Z)
• Understanding robustness and generalization of artificial neural networks through Fourier masks [8.94889125739046]
  Recent literature suggests that robust networks with good generalization properties tend to be biased towards processing low frequencies in images. We develop an algorithm that allows us to learn modulatory masks highlighting the essential input frequencies needed for preserving a trained network's performance.
  arXiv  Detail & Related papers  (2022-03-16T17:32:00Z)
• The Spectral Bias of Polynomial Neural Networks [63.27903166253743]
  Polynomial neural networks (PNNs) have been 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 $textitspectral bias$ 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 Tangent Kernel (NTK) of PNNs. We find that the $Pi$-Net family, i.e., a recently proposed parametrization of PNNs, speeds up the
  arXiv  Detail & Related papers  (2022-02-27T23:12:43Z)
• Spatial Frequency Bias in Convolutional Generative Adversarial Networks [14.564246294896396]
  We show that the ability of convolutional GANs to learn a distribution is significantly affected by the spatial frequency of the underlying carrier signal. We show that this bias is not merely a result of the scarcity of high frequencies in natural images, rather, it is a systemic bias hindering the learning of high frequencies regardless of their prominence in a dataset.
  arXiv  Detail & Related papers  (2020-10-04T03:05:29Z)
• Robust Learning with Frequency Domain Regularization [1.370633147306388]
  We introduce a new regularization method by constraining the frequency spectra of the filter of the model. We demonstrate the effectiveness of our regularization by (1) defensing to adversarial perturbations; (2) reducing the generalization gap in different architecture; and (3) improving the generalization ability in transfer learning scenario without fine-tune.
  arXiv  Detail & Related papers  (2020-07-07T07:29:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.