arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2001.08370cs.LGstat.ML
收藏

随机矩阵理论证明GAN数据的深度学习表示表现为高斯混合

Random Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixtures

CEA List(法国原子能委员会列表研究所);Centralesupélec(法国中央理工-高等电力学院);GIPSA-Lab(格勒诺布尔交互性物理系统与自动化实验室)

Mohamed El Amine Seddik, Cosme Louart, Mohamed Tamaazousti, Romain Couillet

摘要:

本文表明,生成对抗网络(GANs)产生的数据的深度学习(DL)表示是属于所谓的\textit{concentrated}随机向量类的随机向量。进一步利用来自混合模型的具有$X=[x_1,\ldots,x_n]\in \mathbb{R}^{p\times n}$和$x_i$独立集中随机向量的$G = X^T X$类型的Gram矩阵渐近地表现(作为$n,p\to \infty$),就好像$x_i$是从高斯混合物中提取的,这表明GAN数据的DL表示可以通过它们的前两个统计矩来完全描述,用于广泛的标准分类器。我们的理论研究结果通过使用BigGAN模型和不同流行的深度表示网络生成图像来验证。

英文摘要:

This paper shows that deep learning (DL) representations of data produced by generative adversarial nets (GANs) are random vectors which fall within the class of so-called \textit{concentrated} random vectors. Further exploiting the fact that Gram matrices, of the type $G = X^T X$ with $X=[x_1,\ldots,x_n]\in \mathbb{R}^{p\times n}$ and $x_i$ independent concentrated random vectors from a mixture model, behave asymptotically (as $n,p\to \infty$) as if the $x_i$ were drawn from a Gaussian mixture, suggests that DL representations of GAN-data can be fully described by their first two statistical moments for a wide range of standard classifiers. Our theoretical findings are validated by generating images with the BigGAN model and across different popular deep representation networks.

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。

↑