Learning Implicit Generative Models with the Method of Learned Moments

Abstract

We propose a method of moments (MoM) algorithm for training large-scale implicit generative models. Moment estimation in this setting encounters two problems: it is often difficult to define the millions of moments needed to learn the model parameters, and it is hard to determine which properties are useful when specifying moments. To address the first issue, we introduce a moment network, and define the moments as the network's hidden units and the gradient of the network's output with the respect to its parameters. To tackle the second problem, we use asymptotic theory to highlight desiderata for moments -- namely they should minimize the asymptotic variance of estimated model parameters -- and introduce an objective to learn better moments. The sequence of objectives created by this Method of Learned Moments (MoLM) can train high-quality neural image samplers. On CIFAR-10, we demonstrate that MoLM-trained generators achieve significantly higher Inception Scores and lower Frechet Inception Distances than those trained with gradient penalty-regularized and spectrally-normalized adversarial objectives. These generators also achieve nearly perfect Multi-Scale Structural Similarity Scores on CelebA, and can create high-quality samples of 128x128 images.

arXiv commentICML 2018, 6 figures, 17 pages

References in corpus (13)

• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization
• MMD GAN: Towards Deeper Understanding of Moment Matching Network
• The Cramer Distance as a Solution to Biased Wasserstein Gradients
• Variational Approaches for Auto-Encoding Generative Adversarial Networks
• A Note on the Inception Score
• Learning in Implicit Generative Models
• Demystifying MMD GANs
• A Spectral Algorithm for Latent Dirichlet Allocation
• Generative Models and Model Criticism via Optimized Maximum Mean Discrepancy
• Least Squares Generative Adversarial Networks
• FastMMD: Ensemble of Circular Discrepancy for Efficient Two-Sample Test
• McGan: Mean and Covariance Feature Matching GAN

Cited by in corpus (3)

• How to GAN LHC Events
• Prescribed Generative Adversarial Networks
• Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator