# Generative Model with Dynamic Linear Flow

arXiv: https://arxiv.org/abs/1905.03239 · HTML: https://mlsanity.com/paper/1905.03239/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 May 2019.

## Built on by (most cited first, 2 of 2)

- [Jacobian Determinant of Normalizing Flows](https://mlsanity.com/paper/2102.06539/) (2021)
- [BPLF: A Bi-Parallel Linear Flow Model for Facial Expression Generation from Emotion Set Images](https://mlsanity.com/paper/2106.07563/) (2021)

## Abstract (arXiv)

Flow-based generative models are a family of exact log-likelihood models with tractable sampling and latent-variable inference, hence conceptually attractive for modeling complex distributions. However, flow-based models are limited by density estimation performance issues as compared to state-of-the-art autoregressive models. Autoregressive models, which also belong to the family of likelihood-based methods, however suffer from limited parallelizability. In this paper, we propose Dynamic Linear Flow (DLF), a new family of invertible transformations with partially autoregressive structure. Our method benefits from the efficient computation of flow-based methods and high density estimation performance of autoregressive methods. We demonstrate that the proposed DLF yields state-of-theart performance on ImageNet 32x32 and 64x64 out of all flow-based methods, and is competitive with the best autoregressive model. Additionally, our model converges 10 times faster than Glow (Kingma and Dhariwal, 2018). The code is available at https://github.com/naturomics/DLF.