Variational Approaches for Auto-Encoding Generative Adversarial Networks

Abstract

Auto-encoding generative adversarial networks (GANs) combine the standard GAN algorithm, which discriminates between real and model-generated data, with a reconstruction loss given by an auto-encoder. Such models aim to prevent mode collapse in the learned generative model by ensuring that it is grounded in all the available training data. In this paper, we develop a principle upon which auto-encoders can be combined with generative adversarial networks by exploiting the hierarchical structure of the generative model. The underlying principle shows that variational inference can be used a basic tool for learning, but with the in- tractable likelihood replaced by a synthetic likelihood, and the unknown posterior distribution replaced by an implicit distribution; both synthetic likelihoods and implicit posterior distributions can be learned using discriminators. This allows us to develop a natural fusion of variational auto-encoders and generative adversarial networks, combining the best of both these methods. We describe a unified objective for optimization, discuss the constraints needed to guide learning, connect to the wide range of existing work, and use a battery of tests to systematically and quantitatively assess the performance of our method.

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Mode Regularized Generative Adversarial Networks
• Learning in Implicit Generative Models
• On distinguishability criteria for estimating generative models
• Variational Inference using Implicit Distributions
• Generative Adversarial Nets from a Density Ratio Estimation Perspective
• Comparison of Maximum Likelihood and GAN-based training of Real NVPs
• Adversarial Message Passing For Graphical Models

Cited by in corpus (9)

• Large-Scale 3D Shape Reconstruction and Segmentation from ShapeNet Core55
• O-GAN: Extremely Concise Approach for Auto-Encoding Generative Adversarial Networks
• Statistical Parametric Speech Synthesis Using Generative Adversarial Networks Under A Multi-task Learning Framework
• Image Quality Assessment Techniques Show Improved Training and Evaluation of Autoencoder Generative Adversarial Networks
• DualDis: Dual-Branch Disentangling with Adversarial Learning
• Generative adversarial network based on chaotic time series
• Auto-Embedding Generative Adversarial Networks for High Resolution Image Synthesis
• Capturing the diversity of biological tuning curves using generative adversarial networks
• WAYLA - Generating Images from Eye Movements