SGD Learns One-Layer Networks in WGANs
SGD Learns One-Layer Networks in WGANs
复制标题
DOI:
--
复制
发表时间:
2019-10
期刊:
影响因子:
--
通讯作者:
Qi Lei;J. Lee;A. Dimakis;C. Daskalakis
中科院分区:
文献类型:
--
作者:
Qi Lei;J. Lee;A. Dimakis;C. Daskalakis
Generative adversarial networks (GANs) are a widely used framework for learning generative models. Wasserstein GANs (WGANs), one of the most successful variants of GANs, require solving a minmax optimization problem to global optimality, but are in practice successfully trained using stochastic gradient descent-ascent. In this paper, we show that, when the generator is a one-layer network, stochastic gradient descent-ascent converges to a global solution with polynomial time and sample complexity.