Flow-based generative models are a family of exact log-likelihood models withtractable sampling and latent-variable inference, hence conceptually attractive formodeling complex distributions. However, flow-based models are limited by den-sity estimation performance issues as compared to state-of-the-art autoregressivemodels. Autoregressive models, which also belong to the family of likelihood-based methods, however suffer from limited parallelizability. In this paper, weproposeDynamic Linear Flow (DLF), a new family of invertible transformationswith partially autoregressive structure. Our method benefits from the efficientcomputation of flow-based methods and high density estimation performance ofautoregressive methods. We demonstrate that the proposed DLF yields state-of-the-art performance on ImageNet 32×32 and 64×64 out of all flow-based methods,and is competitive with the best autoregressive model. Additionally, our modelconverges 10 times faster than Glow (Kingma and Dhariwal, 2018). The code isavailable athttps://github.com/naturomics/DLF

Do not miss out on this unique opportunity to get insights from Tarry Singh, leader in AI training and technology. Tarry will share with you his insight and methods for transforming midsize as well as large companies into functioning AI companies in the Europe. Now we are bringing our expertise to Japan! Together with our Country Director we will expand our services in the Japan that will provide enterprise advisory as well as unique AI trainings pertaining to Big Data, Machine Learning and Deep Learning.

Do not miss out on this unique opportunity to get insights from Tarry Singh, leader in AI training and technology. Tarry will share with you his insight and methods for transforming midsize as well as large companies into functioning AI companies in the Europe. Now we are bringing our expertise to The Netherlands! We at deepkapha.ai are delighted to announce our AI training partnership with Startel.  Our CEO Tarry Singh and Startel CEO Marco Wagenveld have combined forces to provide unique AI trainings pertaining to Big Data, Machine Learning and Deep Learning.