Papers of the day   All papers



Wouter van Amsterdam: Bernhard Scholkopf (@bschoelkopf) just published a single author paper titled "Causality for Machine Learning" (; this should probably at the top of the reading list for many people interested in machine learning / AI; @yudapearl @eliasbareinboim

1 replies, 736 likes

Judea Pearl: ML will not be the same in 3-5 years, and ML folks who continue to follow the current data-centric paradigm will find themselves outdated, if not jobless. Take note.

17 replies, 497 likes

Judea Pearl: A very comprehensive, delightful and inspiring paper. Recommended to ALL, not just MANY ML/AI folks. Note also that @bschoelkopf does not perceive me as "polarizing the field" as suggested by @ylecun here: SCM unifies, invites and educates. #Bookofwhy

5 replies, 349 likes

Eric Topol: A big problem with #AI is that it hasn't read and couldn't understand @yudapearl's Book of Why. This easy to understand essay by @bschoelkopf (and inspired by Pearl) takes us through the gaps in ML thinking and reasoning, cause and effect @MPI_IS

5 replies, 191 likes

Mehmet Suzen: @yudapearl @mattshomepage Luckily some high profile ML scientists are investing quite a lot of their research output on causality in ML. Specially Schölkopf

4 replies, 165 likes

Anirudh Goyal: This is probably the most succinct summary of various ways in which causality could be useful for machine learning by @bschoelkopf Highly recommended.

1 replies, 126 likes

ML Review: Causality for Machine Learning By @bschoelkopf Mostly non-technical intro to key causal models and how they can contribute to resolving open ML problems like generalization across domains or "thinking" (i.e., acting in an imagined space)

0 replies, 113 likes

Efstratios Gavves: Fantastic position paper by Scholkopf on causality and the role of time in learning, which I strongly believe in. I can only wish that I would be able to argue half as well at some point 😃

0 replies, 88 likes

Judea Pearl: There's much truth to what you're saying. The idea that there are theoretical impediments to ML methods is hard for ML folks to internalize.And repeated assurances that causal inference is just one aspect of what ML has been doing all along do not encourage them to try.#Bookofwhy

1 replies, 82 likes

Christian Wolf: An excellent and very general paper by @bschoelkopf on causality, and its connections to statistics, physics/dynamical systems and touching subjects like discovering causality, impacts on semi-supervised L., RL, representation learning etc. Enjoyed it.

0 replies, 26 likes

Kyle Cranmer: Bernhard Scholkopf (@bschoelkopf) will be speaking at our #NeurIPS2019 workshop on Machine Learning for Physical Sciences

0 replies, 26 likes

KordingLab: Scholkopf on how Pearl style causality is starting to touch machine learning. H/T @danilobzdok

0 replies, 21 likes

Kostas Kamnitsas: Causality for Machine Learning. Tubingen at it again. (Keeps surprising me how such a small place gave rise to such a great research group. I keep wondering what's the recipe. @MPI_IS )

0 replies, 13 likes

Dr. L λR Y-54: @omarsar0 What about causality for machine learning?

0 replies, 8 likes

Geir Kjetil Sandve: I still find that learning things trumps doing things any day. Thanks to @bschoelkopf and @eliasbareinboim for giving me two distinct, fantastic reading experiences on papers I just recently discovered - and

0 replies, 6 likes

Christian Wolf: I have a single single-author paper, used "We". "I" would just sound very ego-centric to me. Not sure I ever read "I" in a paper, unless it provides personal context, relating several years of research, eg. in, and even here, "we" is used at least as often

2 replies, 6 likes

Amit Sharma: Appropos Bengio's talk at #neurips19, here's a great summary on applying causal reasoning for machine learning problems like generalization and adversarial robustness by @bschoelkopf #causalML

0 replies, 4 likes

Italian Association for Machine Learning: Great review on causality in machine learning by @bschoelkopf :

0 replies, 3 likes

e-Katerina Vylomova: @zacharylipton Also, enjoyed reading Schölkopf's recent paper on Causality for ML: (and "The Book of Why" by Judea Pearl and Dana MacKenzie)

0 replies, 3 likes

Eric Topol: @pradeu Agree, Thomas. Casuality can't be emphasized enough. @yudapearl's book is my favorite source. And it's now coming up with #AI (that it can't)

0 replies, 1 likes

Seyed Mostafa Kia: #CAUSALITY FOR #MACHINE_LEARNING by @bschoelkopf "the hard open problems of machine learning and AI are intrinsically related to causality"

0 replies, 1 likes

Paul S. Conyngham: Causality for Machine learning! read it at 👇

0 replies, 1 likes

Complex Human: Causality for Machine Learning

0 replies, 1 likes

Thread Reader App: @IntuitMachine Guten tag, you can read it here: Thread by @IntuitMachine: High time to read: "Causality for Machine Learning"… by Bernhard… See you soon. 🤖

0 replies, 1 likes

Aaron Snoswell (薛嘉伦): Today's #MachineLearning paper is @bschoelkopf's recent philosophical essay 'Causality for Machine Learning' ( Given an unlabelled scatter plot in arbitrary units, can you tell if X causes Y? Y causes X? There is a common unobserved causal factor? 1/3

1 replies, 1 likes

Juan Arévalo: A must read. The connection between #causality and #MachineLearning by @bschoelkopf

0 replies, 1 likes

Pawan Sasanka Ammanamanchi: Causality in Machine Learning.

0 replies, 1 likes

Nasim: A primer on the emerging connections between Causal Inference and Machine Learning, by @bschoelkopf:

0 replies, 1 likes

Danilo Bzdok: @KordingLab @TheColeLab @sweichwald @f2harrell

0 replies, 1 likes

Boaz: I'm trying to read this paper on causality in machine learning. I did recently listen to an audiobook of Pearl's "The book of Why" and this article seems to be within the same domain.

2 replies, 0 likes


Found on Nov 26 2019 at

PDF content of a computer science paper: CAUSALITY FOR MACHINE LEARNING