Papers of the day   All papers

LEARNING NEURAL CAUSAL MODELS FROM UNKNOWN INTERVENTIONS

Comments

Sanjeev Arora: Workshop: "Theory of Deep Learning: Where Next?" at the Institute for Advanced Study, Tuesday--Friday this week. Amazing schedule of talks! http://www.math.ias.edu/wtdl Registration is closed (sorry), but follow livestream here https://www.ias.edu/livestream

9 replies, 534 likes


will knight: Yoshua Bengio, one of the pioneers of deep learning, now wants to his algorithms to ask 'why' things happen: https://www.wired.com/story/ai-pioneer-algorithms-understand-why/

14 replies, 368 likes


rosemary ke: We have released our code for "Neural causal learning from unknown interventions" here https://github.com/nke001/causal_learning_unknown_interventions. The paper is here https://arxiv.org/pdf/1910.01075.pdf. joint work with Olexa Bilaniuk, @anirudhg9119, @hugo_larochelle, @chrisjpal, Yoshua Bengio

1 replies, 217 likes


rosemary ke: Our recent papers on learning neural causal models from unknown interventions featured on Wired, (https://arxiv.org/abs/1910.01075, https://arxiv.org/abs/1901.10912)

3 replies, 163 likes


Anirudh Goyal: New work out. Learning Neural Causal Models from Unknown Interventions. Work led by @rosemary_ke. https://arxiv.org/abs/1910.01075 Joint work with Olexa Bilaniuk, Stefan Bauer, @hugo_larochelle , Chris Pal, Yoshua Bengio. @MILAMontreal. A short summary:

1 replies, 101 likes


rosemary ke: Our new work on learning Neural Causal Models from unknown interventions! In the real world, interventions are also not always performed by an experimenter. They can be performed by other agents, or by environmental changes in unknown ways and hence are unknown to the model. https://t.co/MiMP3NeCiS

2 replies, 97 likes


Elias Bareinboim: 1/12 Brdly spk, assuming one can infer the effect of an intervention when experimental data matching exactly this intervention is available is not surprising, causally-speaking. Why? There's no cross-rung inference, but a typical function approx exercise. This is Judea's main...

3 replies, 37 likes


Anirudh Goyal: Our recent work on learning neural causal models featured on Wired (https://arxiv.org/abs/1910.01075, https://arxiv.org/abs/1901.10912)

0 replies, 26 likes


rosemary ke: Attending the IAS workshop, will be presenting our work on neural causal learning from unknown interventions. https://arxiv.org/abs/1910.01075 😃

0 replies, 20 likes


MONTREAL.AI: Learning Neural Causal Models from Unknown Interventions Nan Rosemary Ke, Olexa Bilaniuk, Anirudh Goyal, Stefan Bauer, Hugo Larochelle, Chris Pal, Yoshua Bengio : https://arxiv.org/abs/1910.01075 #CausalModels #MachineLearning #ArtificialIntelligence https://t.co/f5lFBImPoK

0 replies, 18 likes


rosemary ke: A talk about our paper can be found at Yoshua's NeurIPS 2019 keynote lecture. The video and slides are available at https://slideslive.com/38921750/from-system-1-deep-learning-to-system-2-deep-learning

0 replies, 13 likes


Vincent Boucher 🕊: Pre-Debate Material Learning Neural Causal Models from Unknown Interventions Ke et al.: https://arxiv.org/abs/1910.01075 #AIDebate #MachineLearning #ArtificialIntelligence https://t.co/7zjraRQY1R

0 replies, 10 likes


Anirudh Goyal: @rosemary_ke will be talking in Causal Learning workshop #NeurIPS2019 Learning Neural Causal Models from Unknown Interventions. https://arxiv.org/abs/1910.01075 Joint work with Olexa Bilaniuk, Stefan Bauer, @hugo_larochelle, @chrisjpal, Yoshua Bengio. @MILAMontreal Give us feedback! :)

1 replies, 8 likes


Danilo J. Rezende: Nice paper from @rosemary_ke et al!

0 replies, 6 likes


Stanisław Jastrzębski: @yudapearl @GaryMarcus @moultano What precisely do you mean by "mathematical impossibility"? Causal graph can be inferred if observations are sampled using different random interventions. Such inference can be done using DL https://arxiv.org/abs/1910.01075. Then CI can be done on top using another DL model

2 replies, 5 likes


Anirudh Goyal: See, also the followup to this led by @rosemary_ke : ) https://arxiv.org/abs/1910.01075

0 replies, 5 likes


rosemary ke: The poster session is happening now

0 replies, 2 likes


Content

Found on Oct 14 2019 at https://arxiv.org/pdf/1910.01075.pdf

PDF content of a computer science paper: LEARNING NEURAL CAUSAL MODELS FROM UNKNOWN INTERVENTIONS