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 2302.13183stat.MLcs.LG
收藏

关于流形上分布逼近与估计的深生成模型

On Deep Generative Models for Approximation and Estimation of Distributions on Manifolds

Georgia Institute of Technology(佐治亚理工学院);Princeton University(普林斯顿大学)

Biraj Dahal, Alex Havrilla, Minshuo Chen, Tuo Zhao, Wenjing Liao

摘要:

生成网络在分布学习方面取得了巨大的经验性成功。许多现有的实验已经证明,生成网络可以从低维的易于样本分布生成高维复杂数据。然而,这一现象不能被现有的理论所证明。广泛持有的流形假设推测,真实世界的数据集,如自然图像和信号,表现出低维的几何结构。在本文中,我们考虑这样的低维数据结构,假设数据分布支持低维流形。我们证明了Wasserstein-1损失下生成网络的统计保证。我们表明,Wasserstein-1损失收敛到零,在一个快速的速度取决于内在的尺寸,而不是周围的数据尺寸。我们的理论利用了数据集中的低维几何结构,并证明了生成网络的实用能力。我们不需要对数据分布进行平滑假设,这在实践中是可取的。

英文摘要:

Generative networks have experienced great empirical successes in distribution learning. Many existing experiments have demonstrated that generative networks can generate high-dimensional complex data from a low-dimensional easy-to-sample distribution. However, this phenomenon can not be justified by existing theories. The widely held manifold hypothesis speculates that real-world data sets, such as natural images and signals, exhibit low-dimensional geometric structures. In this paper, we take such low-dimensional data structures into consideration by assuming that data distributions are supported on a low-dimensional manifold. We prove statistical guarantees of generative networks under the Wasserstein-1 loss. We show that the Wasserstein-1 loss converges to zero at a fast rate depending on the intrinsic dimension instead of the ambient data dimension. Our theory leverages the low-dimensional geometric structures in data sets and justifies the practical power of generative networks. We require no smoothness assumptions on the data distribution which is desirable in practice.

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。

↑