MATH - PhD Student Seminar - Approximation and generalization bounds for generative adversarial networks

10:00am - 11:00am
https://hkust.zoom.us/j/5906683526 (Passcode: 5956)

The remarkable empirical performance of Generative Adversarial Networks (GANs) in generating high-quality samples have attracted enormous attention in the past few years. In this talk, we discuss how well can GANs approximate and learn high-dimensional distributions. We show that deep ReLU neural networks can transform a low-dimensional source distribution to a distribution that is arbitrarily close to a high-dimensional target distribution in Wasserstein distance. The approximation order only depends on the intrinsic dimension of the target distribution. While only finite samples are observed, we prove that GANs are consistent estimators of the data distributions under Wasserstein distance, if the generator and discriminator network architectures are properly chosen. Furthermore, the convergence rates do not depend on the high ambient dimension, but on the lower intrinsic dimension of target distribution, which implies GANs can overcome the curse of dimensionality.

日期
时间
10:00am - 11:00am
地点
https://hkust.zoom.us/j/5906683526 (Passcode: 5956)
讲者/ 表演者:
Mr. Yunfei YANG
语言
英文
适合对象
校友
教职员
研究生
本科生
主办单位
数学系
新增活动
请各校内团体将活动发布至大学活动日历。