Comparing Spectral Bias and Robustness For Two-Layer Neural Networks: SGD vs Adaptive Random Fourier Features

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kammonen, Aku, Liang, Lisi, Pandey, Anamika, Tempone, Raúl
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917580258672640
author Kammonen, Aku
Liang, Lisi
Pandey, Anamika
Tempone, Raúl
author_facet Kammonen, Aku
Liang, Lisi
Pandey, Anamika
Tempone, Raúl
contents We present experimental results highlighting two key differences resulting from the choice of training algorithm for two-layer neural networks. The spectral bias of neural networks is well known, while the spectral bias dependence on the choice of training algorithm is less studied. Our experiments demonstrate that an adaptive random Fourier features algorithm (ARFF) can yield a spectral bias closer to zero compared to the stochastic gradient descent optimizer (SGD). Additionally, we train two identically structured classifiers, employing SGD and ARFF, to the same accuracy levels and empirically assess their robustness against adversarial noise attacks.
format Preprint
id arxiv_https___arxiv_org_abs_2402_00332
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Comparing Spectral Bias and Robustness For Two-Layer Neural Networks: SGD vs Adaptive Random Fourier Features
Kammonen, Aku
Liang, Lisi
Pandey, Anamika
Tempone, Raúl
Machine Learning
We present experimental results highlighting two key differences resulting from the choice of training algorithm for two-layer neural networks. The spectral bias of neural networks is well known, while the spectral bias dependence on the choice of training algorithm is less studied. Our experiments demonstrate that an adaptive random Fourier features algorithm (ARFF) can yield a spectral bias closer to zero compared to the stochastic gradient descent optimizer (SGD). Additionally, we train two identically structured classifiers, employing SGD and ARFF, to the same accuracy levels and empirically assess their robustness against adversarial noise attacks.
title Comparing Spectral Bias and Robustness For Two-Layer Neural Networks: SGD vs Adaptive Random Fourier Features
topic Machine Learning
url https://arxiv.org/abs/2402.00332