PolyGAN：高阶多项式生成器
PolyGAN: High-Order Polynomial Generators
摘要：
生成对抗网络（GANs）已经成为学习高维分布生成模型的黄金标准。自从它们出现以来，GANs的许多变体已经在文献中介绍，主要集中在利用新的损失函数，优化/正则化策略和网络架构。在本文中，我们把我们的注意力转向发电机和调查使用高阶多项式作为替代类的通用函数逼近。具体地说，我们提出了PolyGAN，其中我们通过高阶多项式来建模数据生成器，其未知参数自然由高阶张量表示。我们介绍了两个张量分解，显着减少参数的数量，并显示它们如何可以有效地实现分层神经网络，只采用线性/卷积块。我们展示了第一次，通过使用我们的方法，GAN生成器可以近似的数据分布，而不使用任何激活函数。对合成数据和真实数据（图像和3D点云）的全面实验评估证明了PolyGAN相对于最先进技术的优点。
英文摘要：
Generative Adversarial Networks (GANs) have become the gold standard when it comes to learning generative models for high-dimensional distributions. Since their advent, numerous variations of GANs have been introduced in the literature, primarily focusing on utilization of novel loss functions, optimization/regularization strategies and network architectures. In this paper, we turn our attention to the generator and investigate the use of high-order polynomials as an alternative class of universal function approximators. Concretely, we propose PolyGAN, where we model the data generator by means of a high-order polynomial whose unknown parameters are naturally represented by high-order tensors. We introduce two tensor decompositions that significantly reduce the number of parameters and show how they can be efficiently implemented by hierarchical neural networks that only employ linear/convolutional blocks. We exhibit for the first time that by using our approach a GAN generator can approximate the data distribution without using any activation functions. Thorough experimental evaluation on both synthetic and real data (images and 3D point clouds) demonstrates the merits of PolyGAN against the state of the art.
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。
