arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.00352stat.MLcs.LG
收藏

生成式对抗网络的重参数采样

Reparameterized Sampling for Generative Adversarial Networks

Peking University(北京大学)

Yifei Wang, Yisen Wang, Jiansheng Yang, Zhouchen Lin

摘要:

近年来,采样方法已被成功地应用于提高生成对抗网络(GANs)的样本质量。然而,在实践中,它们通常具有较差的采样效率,因为来自生成器的独立建议采样。在这项工作中,我们提出了REP-GAN,一种新的采样方法,允许一般依赖的建议,通过REparameterizing的马尔可夫链的潜在空间的生成器。从理论上讲,我们表明,我们的重新参数化的建议承认一个封闭形式的大都会黑斯廷斯验收比。在人工和真实数据集上的大量实验表明,我们的REP-GAN大大提高了样本效率,同时获得了更好的样本质量。

英文摘要:

Recently, sampling methods have been successfully applied to enhance the sample quality of Generative Adversarial Networks (GANs). However, in practice, they typically have poor sample efficiency because of the independent proposal sampling from the generator. In this work, we propose REP-GAN, a novel sampling method that allows general dependent proposals by REParameterizing the Markov chains into the latent space of the generator. Theoretically, we show that our reparameterized proposal admits a closed-form Metropolis-Hastings acceptance ratio. Empirically, extensive experiments on synthetic and real datasets demonstrate that our REP-GAN largely improves the sample efficiency and obtains better sample quality simultaneously.

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。

↑