论文标题
神经网络的确切光谱规范正规化
Exact Spectral Norm Regularization for Neural Networks
论文作者
论文摘要
我们追求一系列研究，旨在使深度神经网络的输入输出映射的雅各布频谱规范正规化。尽管以前的工作依赖上限技术，但我们提供了一个针对确切光谱规范的方案。我们显示，与以前的光谱正则化技术相比，我们的算法可以提高概括性能，同时保持了防御自然和对抗性噪声的强大保护。此外，我们进一步探讨了一些以前的推理，这些推理是关于雅各布正规化提供的强大对抗保护，并表明它可能具有误导性。
We pursue a line of research that seeks to regularize the spectral norm of the Jacobian of the input-output mapping for deep neural networks. While previous work rely on upper bounding techniques, we provide a scheme that targets the exact spectral norm. We showcase that our algorithm achieves an improved generalization performance compared to previous spectral regularization techniques while simultaneously maintaining a strong safeguard against natural and adversarial noise. Moreover, we further explore some previous reasoning concerning the strong adversarial protection that Jacobian regularization provides and show that it can be misleading.
