arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.05068cs.LG
收藏

控制复杂度和Lipschitz常数改进多项式网络

Controlling the Complexity and Lipschitz Constant improves polynomial nets

EPFL(洛桑联邦理工学院)

Zhenyu Zhu, Fabian Latorre, Grigorios G Chrysos, Volkan Cevher

摘要:

虽然多项式网络类表现出与神经网络(NN)相当的性能,但它目前既没有理论上的泛化特性,也没有鲁棒性保证。为此,我们得到了新的复杂性边界的集合的耦合CP-分解(CCP)和嵌套耦合CP-分解(NCP)模型的多项式网的$\ell_\infty$ -运营商范数和$\ell_2$ -运营商范数。此外,我们推导出两个模型的Lipschitz常数的界限,以建立其稳健性的理论证明。理论结果使我们能够提出一个原则性的正则化方案,我们还在六个数据集上进行了实验评估,并表明它提高了模型对对抗性扰动的准确性和鲁棒性。我们展示了如何将这种正则化与对抗训练相结合,从而实现进一步的改进。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑