Generative Latent Flow

Abstract

In this work, we propose the Generative Latent Flow (GLF), an algorithm for generative modeling of the data distribution. GLF uses an Auto-encoder (AE) to learn latent representations of the data, and a normalizing flow to map the distribution of the latent variables to that of simple i.i.d noise. In contrast to some other Auto-encoder based generative models, which use various regularizers that encourage the encoded latent distribution to match the prior distribution, our model explicitly constructs a mapping between these two distributions, leading to better density matching while avoiding over regularizing the latent variables. We compare our model with several related techniques, and show that it has many relative advantages including fast convergence, single stage training and minimal reconstruction trade-off. We also study the relationship between our model and its stochastic counterpart, and show that our model can be viewed as a vanishing noise limit of VAEs with flow prior. Quantitatively, under standardized evaluations, our method achieves state-of-the-art sample quality among AE based models on commonly used datasets, and is competitive with GANs' benchmarks.

References in corpus (33)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Large Scale GAN Training for High Fidelity Natural Image Synthesis
• Spectral Normalization for Generative Adversarial Networks
• Neural Discrete Representation Learning
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• On the Convergence of Adam and Beyond
• Pixel Recurrent Neural Networks
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• NICE: Non-linear Independent Components Estimation
• NIPS 2016 Tutorial: Generative Adversarial Networks
• Density estimation using Real NVP
• Disentangling by Factorising
• Style Transfer from Non-Parallel Text by Cross-Alignment
• VEEGAN: Reducing Mode Collapse in GANs using Implicit Variational Learning
• A note on the evaluation of generative models
• Importance Weighted Autoencoders
• Generalization and Equilibrium in Generative Adversarial Nets (GANs)
• Optimizing the Latent Space of Generative Networks
• Wasserstein Auto-Encoders
• Assessing Generative Models via Precision and Recall
• Sylvester Normalizing Flows for Variational Inference
• On Unifying Deep Generative Models
• Diagnosing and Enhancing VAE Models
• Implicit Maximum Likelihood Estimation
• VAE with a VampPrior
• Distribution Matching in Variational Inference
• Learnable Explicit Density for Continuous Latent Space and Variational Inference
• Resampled Priors for Variational Autoencoders
• Learning Hierarchical Priors in VAEs

Cited by in corpus (8)

• Likelihood Regret: An Out-of-Distribution Detection Score For Variational Auto-encoder
• ControlVAE: Controllable Variational Autoencoder
• A Method to Model Conditional Distributions with Normalizing Flows
• Cooperative Training of Fast Thinking Initializer and Slow Thinking Solver for Conditional Learning
• Sliced Iterative Normalizing Flows
• Exponential Tilting of Generative Models: Improving Sample Quality by Training and Sampling from Latent Energy
• ControlVAE: Tuning, Analytical Properties, and Performance Analysis
• Variance Constrained Autoencoding