Flow-based generative models are powerful exact likelihood models with efficient sampling and inference. Despite their computational efficiency, flow-based models generally have much worse density modeling performance compared to state-of-the-art autoregressive models. In this paper, we investigate and improve upon three limiting design choices employed by flow-based models in prior work: the use of uniform noise for dequantization, the use of inexpressive affine flows, and the use of purely convolutional conditioning networks in coupling layers. Based on our findings, we propose Flow++, a new flow-based model that is now the state-of-the-art non-autoregressive model for unconditional density estimation on standard image benchmarks. Our work has begun to close the significant performance gap that has so far existed between autoregressive models and flow-based models. Our implementation is available at https://github.com/aravindsrinivas/flowpp
@article{arxiv.1902.00275,
title = {Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design},
author = {Jonathan Ho and Xi Chen and Aravind Srinivas and Yan Duan and Pieter Abbeel},
journal= {arXiv preprint arXiv:1902.00275},
year = {2019}
}