Deconstructing Generative Adversarial Networks
From MaRDI portal
Abstract: 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 error and statistical error in GANs, and show how to apply our principle with empirical samples to predict how many samples are sufficient for GANs in order not to suffer from the discriminator winning problem. 3. Optimization: we demonstrate alternating gradient descent is provably not locally asymptotically stable in optimizing the GAN formulation of PCA. We diagnose the problem as the minimax duality gap being non-zero, and propose a new GAN architecture whose duality gap is zero, where the value of the game is equal to the previous minimax value (not the maximin value). We prove the new GAN architecture is globally asymptotically stable in optimization under alternating gradient descent.
Cited in
(17)- Generative adversarial networks with decoder-encoder output noises
- Generative adversarial networks are special cases of artificial curiosity (1990) and also closely related to predictability minimization (1991)
- Rectified binary convolutional networks with generative adversarial learning
- Generalization error of GAN from the discriminator's perspective
- Some theoretical properties of GANs
- Embedding decision diagrams into generative adversarial networks
- scientific article; zbMATH DE number 7403502 (Why is no real title available?)
- scientific article; zbMATH DE number 7027884 (Why is no real title available?)
- scientific article; zbMATH DE number 7626743 (Why is no real title available?)
- Interpretable Generative Adversarial Networks With Exponential Function
- scientific article; zbMATH DE number 7306864 (Why is no real title available?)
- Pursuit of a discriminative representation for multiple subspaces via sequential games
- Stochastic differential equation approximations of generative adversarial network training and its long-run behavior
- Connecting GANs, mean-field games, and optimal transport
- Statistical guarantees for distribution estimation of contaminated data via DNN-based MoM-GANs
- Distribution estimation for time series via DNN-based GANs with an application to change-point estimation
- Robust estimation for kernel exponential families with smoothed total variation distances
This page was built for publication: Deconstructing Generative Adversarial Networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5138883)
