While the class of Polynomial Nets demonstrates comparable performance to neural networks (NN), it currently has neither theoretical generalization characterization nor robustness guarantees. To this end, we derive new complexity bounds for the set of Coupled CP-Decomposition (CCP) and Nested Coupled CP-decomposition (NCP) models of Polynomial Nets in terms of the $\ell_\infty$-operator-norm and the $\ell_2$-operator norm. In addition, we derive bounds on the Lipschitz constant for both models to establish a theoretical certificate for their robustness. The theoretical results enable us to propose a principled regularization scheme that we also evaluate experimentally in six datasets and show that it improves the accuracy as well as the robustness of the models to adversarial perturbations. We showcase how this regularization can be combined with adversarial training, resulting in further improvements.
翻译:虽然多式网类显示了与神经网络(NN)相似的性能,但目前它既没有理论上的概括性定性,也没有稳健性的保证。为此,我们为一套多式网模式的组合式CP-Decomposition(CCP)和Nested 组合式CP-decomposition(NCP)模型(NCP)带来了新的复杂界限,即$\ ⁇ inty$-operator-norm 和$\ell_2$-operator 规范。此外,我们从利普西茨常数中提取了界限,使两个模型都能够为它们的稳健性建立理论证书。理论结果使我们能够提出一个有原则的规范化计划,我们也在六个数据集中进行实验性评估,并表明它提高了模型的准确性和稳健性以对抗性扰动性。我们展示了这种规范化如何与对抗性训练相结合,从而导致进一步的改进。