Can I read Deconstructing Generative Adversarial Networks on EtoBox?

Deconstructing Generative Adversarial Networks by Zhu, Banghua; Jiao, Jiantao; Tse, David is a scholarly article available to read on EtoBox.

What is Deconstructing Generative Adversarial Networks about?

We deconstruct the performance of GANs into three components: 1. Formulation: we propose a perturbation view of the population target of GANs. Building on this interpretation, we show that GANs can be viewed as a generalization of the robust statistics framework, and propose a novel GAN architecture, termed as Cascade GANs, to provably recover meaningful low-dimensional generator approximations when the real distribution is high-dimensional and corrupted by outliers. 2. Generalization: given a population target of GANs, we design a systematic principle, projection under admissible distance, to design GANs to meet the population requirement using finite samples. We implement our principle in three cases to achieve polynomial and sometimes near-optimal sample complexities: (1) learning an arbitrary generator under an arbitrary pseudonorm; (2) learning a Gaussian location family under TV distance, where we utilize our principle provide a new proof for the optimality of Tukey median viewed as GANs; (3) learning a low-dimensional Gaussian approximation of a high-dimensional arbitrary distribution under Wasserstein distance. We demonstrate a fundamental trade-off in the approximation err

Author

Zhu, Banghua; Jiao, Jiantao; Tse, David

Published

2019

Language

EN