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

link管理

链接快照平台

输入网页链接，自动生成快照
标签化管理网页链接

相关文章推荐

乐观的小刀 · 有哪些web网页的电力系统建模开源软件？ ...· 1 月前 ·

英俊的罐头 · 城镇职工参保人员信息变更· 3 月前 ·

寂寞的筷子 · 丁鹿学堂前端路 - 知乎· 9 月前 ·

淡定的保温杯 · java对象转byte[]数组，byte[] ...· 10 月前 ·

想出国的乌龙茶 · 山下诚一郎搜索结果 - 樱花动漫· 10 月前 ·

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. 中文翻译：

推荐文章

乐观的小刀 · 有哪些web网页的电力系统建模开源软件？ - CSDN文库

1 月前

英俊的罐头 · 城镇职工参保人员信息变更

3 月前

寂寞的筷子 · 丁鹿学堂前端路 - 知乎

9 月前

淡定的保温杯 · java对象转byte[]数组，byte[] 数组转java对象，demo - 梦幻朵颜 - 博客园

10 月前

想出国的乌龙茶 · 山下诚一郎搜索结果 - 樱花动漫

10 月前