Understanding GANs via Generalization Analysis for Disconnected Support
This paper provides theoretical analysis of generative adversarial networks (GANs) to explain its advantages over other standard methods of learning probability measures. GANs learn a probability through observations, using the objective function with a generator and a discriminator. While many empirical results indicate that GANs can generate realistic samples, the reason for such successful performance remains unelucidated. This paper focuses the situation where the target probability measure satisfies the disconnected support property, which means a separate support of a probability, and relates it with the advantage of GANs. It is theoretically shown that, unlike other popular models, GANs do not suffer from the decrease of generalization performance caused by the disconnected support property. We rigorously quantify the generalization performance of GANs of a given architecture, and compare it with the performance of the other models. Based on the theory, we also provide a guideline for selecting deep network architecture for GANs. We demonstrate some numerical examples which support our results.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Disconnected Manifold Learning for Generative Adversarial Networks
Natural images may lie on a union of disjoint manifolds rather than one globally connected manifold, and this can cause several difficulties for the training of common Generative Adversarial Networks (GANs). In this work…
Topo Sampler: A Topology Constrained Noise Sampling for GANs
This work studies disconnected manifold learning in generative models in the light of point-set topology and persistent homology. Under this formalism, the topological similarity of latent space in generative models with…
Learning disconnected manifolds: a no GANs land
Typical architectures of Generative AdversarialNetworks make use of a unimodal latent distribution transformed by a continuous generator. Consequently, the modeled distribution always has connected support which is cumbe…
Mode Collapse and Regularity of Optimal Transportation Maps
This work builds the connection between the regularity theory of optimal transportation map, Monge-Amp\`{e}re equation and GANs, which gives a theoretic understanding of the major drawbacks of GANs: convergence difficult…
Ensembles of Generative Adversarial Networks for Disconnected Data
Most current computer vision datasets are composed of disconnected sets, such as images from different classes. We prove that distributions of this type of data cannot be represented with a continuous generative network …