Current advertisement:
NeurIPS 2022 Workshop on neuro Causal and Symbolic AI - submit your work and/or join the online event!"If the discussions become too causal, then we might as well make it more casual." (warning: a joke that requires looking closely)
🌐 Everything to be found in our Slack Community:
We keep a long list of interesting papers (see list in #general
channel at “List of Potential Next Paper Discussions”), from which we vote for our session papers (vote at #vote
channel), and also recordings from our past sessions all self-enclosed in the Slack community (find in #recordings
channel).
Useful Resources:
- Code Tutorial by Alexandre Drouin on various topics featuring Simpson's paradox, identification through adjustment and estimation using machine learning
- Code Tutorial by Matej Zečević on various topics featuring why we actually need causality, the Pearlian causal hierarchy and bounding causal effects
- “The Book of Why” (2018) by Judea Pearl & Dana Mackenzie for an intuitive, general audience introduction into Pearlian causality
- “Causality” Book (CUP, 2009) by Judea Pearl as the original, rigorous treatise on Pearlian causality
- “Elements of Causal Inference” (MITP, 2017) by Jonas Peters et al. providing different and additional perspective on Pearlian causality especially w.r.t. machine learning
- Lecture Series “Causality” by Jonas Peters (2017) covering key topics from the previously listed literature (focus on Peters et al.)
- Online Course ”Introduction to Causal Inference” by Brady Neal (2020) covering key topics from the previously listed literature (focus on Pearl)
- Lecture “Causal Data Science” by Elias Bareinboim (2019) on several advanced topics as well as future perspectives on the field
- “Causal Inference in Statistics” by Judea Pearl et al. (2016) compressed view on Pearlian causality for a statistics educated audience
Are you interested in Graphs and Geometry for Machine Learning?
If so, then consider joining the Learning on Graphs and Geometry Reading Group.