Papers of the day   All papers

Normalizing Flows for Probabilistic Modeling and Inference

Comments

Danilo J. Rezende: Looking for something to read in your flight to #NeurIPS2019? Read about Normalizing Flows from our extensive review paper (also with new insights on how to think about and derive new flows) https://arxiv.org/abs/1912.02762 with @gpapamak @eric_nalisnick @DeepSpiker @balajiln @shakir_za https://t.co/EWh8Aui7n0

11 replies, 651 likes


George Papamakarios: Check out our extensive review paper on normalizing flows! This paper is the product of years of thinking about flows: it contains everything we know about them, and many new insights. With @eric_nalisnick, @DeepSpiker, @shakir_za, @balajiln. http://arxiv.org/abs/1912.02762 Thread 👇

4 replies, 645 likes


Andrej Karpathy: This is very well done and readable, thank you so much for putting it together! (was starting to be hard to keep track of the individual papers and how they relate) Normalizing Flows are very powerful and should become a part of any deep learning researcher/practitioner's toolbox

5 replies, 479 likes


David Duvenaud: This review on normalizing flows is excellent. It's full of clear writing, precise claims, and useful connections.

0 replies, 146 likes


Eric Nalisnick: Indeed, what better way to spend your flight than immersed in 60 pages of all things flow. Happy to hear any feedback (oversights, clarity issues, etc).

3 replies, 64 likes


Adji Bousso Dieng: @yoavgo Some of my favorite review papers (recent): MC gradient estimation in ML by @shakir_za et al. https://arxiv.org/abs/1906.10652 Normalizing flows by @gpapamak et al. https://arxiv.org/abs/1912.02762 Variational inference (pre-amortization) by Blei et al. (@blei_lab) https://arxiv.org/abs/1601.00670

2 replies, 54 likes


Statistics Papers: Normalizing Flows for Probabilistic Modeling and Inference. http://arxiv.org/abs/1912.02762

0 replies, 53 likes


jörn jacobsen: Fantastic summary of the state of the art and open problems in normalizing flows!

0 replies, 30 likes


Shasha Feng: What's popular with ML in MD now?🤔 Normalizing flows! This review of flow method by Google last Dec: https://arxiv.org/abs/1912.02762 And 2 arkiv papers this month: https://arxiv.org/abs/2002.04913 https://arxiv.org/abs/2002.06707

0 replies, 27 likes


Ari Seff: And for an extensive review, check out the just-released "Normalizing Flows for Probabilistic Modeling and Inference" (https://arxiv.org/abs/1912.02762) from @gpapamak @eric_nalisnick @DeepSpiker @balajiln @shakir_za

0 replies, 13 likes


Adam Kosiorek: The most comprehensive overview of normalizing flows to date!

0 replies, 12 likes


no love deep learning ✈ NeuHYPE19: we'll have open-mic sessions to ignite discussions, as well as invited spotlights! First one will be @eric_nalisnick (@CambridgeMLG & @DeepMindAI ) talking about prospects and challenges of #tractable Inference with #Flows check his survey with @gpapamak https://arxiv.org/abs/1912.02762

1 replies, 9 likes


no love deep learning: @martin_trapp Even without using mixtures one might easily fit those 2D densities with more expressive single models...eg #flows and #autoeegressive ones They *are* also tractable for complete evidence, but not marginals Cf. cool survey by @eric_nalisnick @gpapamak http://arxiv.org/abs/1912.02762

1 replies, 8 likes


Roman Shapovalov: This tutorial is gold. Very accessible, comprehensive, and up-to-date. Thanks @gpapamak et al.!

0 replies, 5 likes


Bo Wang: This is very useful resource for anyone who is interested in deep learning research!

0 replies, 5 likes


Dennis Prangle: One for the ever-lengthening must-read list

1 replies, 4 likes


Hyunjik Kim: Review paper on flows from the experts!

0 replies, 4 likes


Gabriel Bernier-Colborne: Great survey paper on normalizing flows: https://arxiv.org/abs/1912.02762

0 replies, 1 likes


Aravind Srinivas: @CShorten30 @EdwardDixon3 @lilianweng Check out https://arxiv.org/abs/1912.02762 by DeepMind; and @pabbeel 's lecture in Berkeley Unsupervised Learning Class - https://www.youtube.com/watch?v=JBb5sSC0JoY

0 replies, 1 likes


KUNDAN KUMAR: Read it. Amazing!!

0 replies, 1 likes


Content

Found on Dec 06 2019 at https://arxiv.org/pdf/1912.02762.pdf

PDF content of a computer science paper: Normalizing Flows for Probabilistic Modeling and Inference