arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2204.04090cs.LG
收藏

基于神经切线核的单级对抗数据合成

Single-level Adversarial Data Synthesis based on Neural Tangent Kernels

National Tsing Hua University(国立清华大学)

Yu-Rong Zhang, Ruei-Yang Su, Sheng Yen Chou, Shan-Hung Wu

摘要:

摘要生成对抗网络(GANs)在数据合成方面取得了令人印象深刻的性能,并推动了许多应用的发展。然而,GANs由于其双层目标而难以训练,这导致了收敛、模式坍塌和梯度消失的问题。在本文中,我们提出了一个新的生成模型称为生成对抗NTK(GA-NTK),有一个单级目标。GA-NTK保持了对抗学习的精神(这有助于生成合理的数据),同时避免了GANs的训练困难。这是通过用神经切线核(NTK-GP)将神经网络建模为高斯过程来完成的,NTK-GP的训练动态可以完全由封闭形式的公式来描述。我们分析了用梯度下降训练的GA-NTK的收敛性,并给出了收敛的充分条件。我们还进行了大量的实验来研究GA-NTK的优点和局限性,并提出了一些技术,使GA-NTK更实用。

英文摘要:

Abstract Generative adversarial networks (GANs) have achieved impressive performance in data synthesis and have driven the development of many applications. However, GANs are known to be hard to train due to their bilevel objective, which leads to the problems of convergence, mode collapse, and gradient vanishing. In this paper, we propose a new generative model called the generative adversarial NTK (GA-NTK) that has a single-level objective. The GA-NTK keeps the spirit of adversarial learning (which helps generate plausible data) while avoiding the training difficulties of GANs. This is done by modeling the discriminator as a Gaussian process with a neural tangent kernel (NTK-GP) whose training dynamics can be completely described by a closed-form formula. We analyze the convergence behavior of GA-NTK trained by gradient descent and give some sufficient conditions for convergence. We also conduct extensive experiments to study the advantages and limitations of GA-NTK and propose some techniques that make GA-NTK more practical.

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。

↑