论文标题
具有潜在分布学习的最佳运输剂的概括特性
Generalization Properties of Optimal Transport GANs with Latent Distribution Learning
论文作者
论文摘要
生成对抗网络（GAN）框架是概率匹配和现实样本生成的完善范式。尽管最近的关注致力于研究此类模型的理论特性，但仍缺少对主构建块的完整理论理解。在这项工作中，我们专注于具有最佳运输指标作为鉴别因子的生成模型，我们研究了潜在分布和推动图映射（Generator）（生成器）之间的相互作用如何从统计和建模的角度影响性能。通过我们的分析，我们提倡学习潜在分布以及GAN范式中的推送图。我们证明，这可以在样本复杂性方面带来显着优势。
The Generative Adversarial Networks (GAN) framework is a well-established paradigm for probability matching and realistic sample generation. While recent attention has been devoted to studying the theoretical properties of such models, a full theoretical understanding of the main building blocks is still missing. Focusing on generative models with Optimal Transport metrics as discriminators, in this work we study how the interplay between the latent distribution and the complexity of the pushforward map (generator) affects performance, from both statistical and modelling perspectives. Motivated by our analysis, we advocate learning the latent distribution as well as the pushforward map within the GAN paradigm. We prove that this can lead to significant advantages in terms of sample complexity.
