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

相关文章推荐

刚分手的领结 · Laravel后端与托管在Plesk上的Ng ...· 10 月前 ·

心软的打火机 · 行为识别综述-腾讯云开发者社区-腾讯云· 11 月前 ·

个性的红茶 · 公众号AI爆文副业，小赚16055！_写作_ ...· 1 年前 ·

腹黑的香瓜 · pytorch ...· 1 年前 ·

礼貌的领带 · dash第一章：dash的基本组件 - ...· 1 年前 ·

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

刚分手的领结 · Laravel后端与托管在Plesk上的Nginx的Vue前端之间的CORS问题

10 月前

心软的打火机 · 行为识别综述-腾讯云开发者社区-腾讯云

11 月前

个性的红茶 · 公众号AI爆文副业，小赚16055！_写作_收益_流量

1 年前

腹黑的香瓜 · pytorch 中tensor在CPU和GPU之间转换，以及numpy之间的转换_python将tensor(0.2268, device='cuda:0')转换为数据-CSDN博客

1 年前

礼貌的领带 · dash第一章：dash的基本组件 - 蒋古诚 - 博客园

1 年前