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 1809.04542cs.LGstat.ML
收藏

受限f-GAN的感应偏置

The Inductive Bias of Restricted f-GANs

University of California, San Diego(加州大学圣地亚哥分校)

Shuang Liu, Kamalika Chaudhuri

摘要:

生成对抗网络是一种新的统计推断方法,已经取得了很大的经验成功;然而,导致这种成功的因素仍然不清楚。在这项工作中,我们试图分析生成对抗性学习-即,作为生成器和生成器之间的游戏结果的统计推断-以了解它与经典的统计推断解决方案(如最大似然推断和矩量法)的区别。具体来说,我们提供了一种由一种简单形式的生成对抗学习(称为限制性f-GAN)推断的分布的理论表征-其中,f-GAN是给定函数类中的函数,生成器诱导的分布被限制在预先指定的分布类中,目标类似于f-发散的变分形式。我们的结果的一个结果是,对于线性KL-GAN-也就是说,当k是某个特征空间上的线性函数并且f对应于KL发散时-由最佳生成器引起的分布既不是最大似然法,也不是矩量法,而是两者的有趣组合。

英文摘要:

Generative adversarial networks are a novel method for statistical inference that have achieved much empirical success; however, the factors contributing to this success remain ill-understood. In this work, we attempt to analyze generative adversarial learning -- that is, statistical inference as the result of a game between a generator and a discriminator -- with the view of understanding how it differs from classical statistical inference solutions such as maximum likelihood inference and the method of moments. Specifically, we provide a theoretical characterization of the distribution inferred by a simple form of generative adversarial learning called restricted f-GANs -- where the discriminator is a function in a given function class, the distribution induced by the generator is restricted to lie in a pre-specified distribution class and the objective is similar to a variational form of the f-divergence. A consequence of our result is that for linear KL-GANs -- that is, when the discriminator is a linear function over some feature space and f corresponds to the KL-divergence -- the distribution induced by the optimal generator is neither the maximum likelihood nor the method of moments solution, but an interesting combination of both.

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。

↑