A Primal-Dual link between GANs and Autoencoders
Since the introduction of Generative Adversarial Networks (GANs) and Variational Autoencoders (VAE), the literature on generative modelling has witnessed an overwhelming resurgence. The impressive, yet elusive empirical performance of GANs has lead to the rise of many GAN-VAE hybrids, with the hopes of GAN level performance and additional benefits of VAE, such as an encoder for feature reduction, which is not offered by GANs. Recently, the Wasserstein Autoencoder (WAE) was proposed, achieving performance similar to that of GANs, yet it is still unclear whether the two are fundamentally different or can be further improved into a unified model. In this work, we study the $f$-GAN and WAE models and make two main discoveries. First, we find that the $f$-GAN and WAE objectives partake in a primal-dual relationship and are equivalent under some assumptions, which then allows us to explicate the success of WAE. Second, the equivalence result allows us to, for the first time, prove generalization bounds for Autoencoder models, which is a pertinent problem when it comes to theoretical analyses of generative models. Furthermore, we show that the WAE objective is related to other statistical quantities such as the $f$-divergence and in particular, upper bounded by the Wasserstein distance, which then allows us to tap into existing efficient (regularized) optimal transport solvers. Our findings thus present the first primal-dual relationship between GANs and Autoencoder models, comment on generalization abilities and make a step towards unifying these models.
Code (0)
등록된 구현이 없습니다.
Tasks
Generalization BoundsMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Adversarial Networks and Autoencoders: The Primal-Dual Relationship and Generalization Bounds
Since the introduction of Generative Adversarial Networks (GANs) and Variational Autoencoders (VAE), the literature on generative modelling has witnessed an overwhelming resurgence. The impressive, yet elusive empirical …
Generalization BoundsTraining Generative Adversarial Networks via Primal-Dual Subgradient Methods: A Lagrangian Perspective on GAN
We relate the minimax game of generative adversarial networks (GANs) to finding the saddle points of the Lagrangian function for a convex optimization problem, where the discriminator outputs and the distribution of gene…
Understand the dynamics of GANs via Primal-Dual Optimization
Generative adversarial network (GAN) is one of the best known unsupervised learning techniques these days due to its superior ability to learn data distributions. In spite of its great success in applications, GAN is kno…
Generative Adversarial NetworkMulti-Task LearningThe Information Autoencoding Family: A Lagrangian Perspective on Latent Variable Generative Models
A large number of objectives have been proposed to train latent variable generative models. We show that many of them are Lagrangian dual functions of the same primal optimization problem. The primal problem optimizes th…
Generative Adversarial Networks for Multimodal Representation Learning in Video Hyperlinking
Continuous multimodal representations suitable for multimodal information retrieval are usually obtained with methods that heavily rely on multimodal autoencoders. In video hyperlinking, a task that aims at retrieving vi…
Information RetrievalRepresentation LearningRetrieval