[1908.09257] Normalizing Flows: Introduction and Ideas

Normalizing Flows are generative models which produce tractable distributions where both sampling and density evaluation can be efficient and exact. The goal of this survey article is to give a coherent and comprehensive review of the literature around the construction and use of Normalizing Flows for distribution learning. We aim to provide context and explanation of the models, review current state-of-the-art literature, and identify open questions and promising future directions.

1 mentions: @shion_honda
Date: 2019/09/09 15:47

Referring Tweets

@shion_honda Normalizing Flows: Introduction and Ideas [Kobyzev+, 2019] GANやVAEと異なり対数尤度を直接最大化する深層生成モデルであるNormalizing Flowのサーベイ。カップリング、自己回帰、残差、ODEなどに分けて最新手法までを扱う。現在のSOTAはFlow++。 t.co/KxP6UkuLt7 #NowReading t.co/28EvzTsl2I

Related Entries

Read more Survey of Scientific Publication Analysis by NLP and CV
1 users, 4 mentions 2019/08/15 08:16
Read more [1911.12116] Analysis of Explainers of Black Box Deep Neural Networks for Computer Vision: A Survey
0 users, 4 mentions 2019/11/28 23:20
Read more [1910.09399] A Survey and Taxonomy of Adversarial Neural Networks for Text-to-Image Synthesis
0 users, 5 mentions 2019/10/26 03:49
Read more [1809.02165] Deep Learning for Generic Object Detection: A Survey
0 users, 0 mentions 2018/09/10 03:23
Read more A Survey on Cross-Modal Embedding
1 users, 1 mentions 2019/08/15 09:46