Augmented Normalizing Flows: Bridging the Gap Between Generative Flows and Latent Variable Models
arXiv:2002.07101
Abstract
In this work, we propose a new family of generative flows on an augmented data space, with an aim to improve expressivity without drastically increasing the computational cost of sampling and evaluation of a lower bound on the likelihood. Theoretically, we prove the proposed flow can approximate a Hamiltonian ODE as a universal transport map. Empirically, we demonstrate state-of-the-art performance on standard benchmarks of flow-based generative modeling.
27 pages, 12 figures
References in corpus (15)
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- NICE: Non-linear Independent Components Estimation
- Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
- Variational Lossy Autoencoder
- Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design
- Improving Variational Auto-Encoders using Householder Flow
- PixelVAE: A Latent Variable Model for Natural Images
- High-Dimensional Probability Estimation with Deep Density Models
- Emerging Convolutions for Generative Normalizing Flows
- Hybrid Models with Deep and Invertible Features
- Calibrating Energy-based Generative Adversarial Networks
- Generative Adversarial Networks as Variational Training of Energy Based Models
- Learnable Explicit Density for Continuous Latent Space and Variational Inference
- Improving Exploration in Soft-Actor-Critic with Normalizing Flows Policies
- Deep Variational Inference Without Pixel-Wise Reconstruction