Time: TTh 11-12:15pm
Location: Taft Hall 216
Instructor: Prof. Elena Zheleva
Office hours: TBD, SEO 1140
Two roads diverged in a yellow wood,
And sorry I could not travel both [...]
I took the one less traveled by,
And that has made all the difference.
"The dramatic success in machine learning has led to an explosion of
AI applications and increasing expectations for autonomous systems that exhibit human-level intelligence. These expectations, however,
have met with fundamental obstacles that cut across many application areas. [... One of the obstacles] concerns the understanding of cause-effect connections. This hallmark of human cognition is [...] a necessary (though not sufficient) ingredient for achieving human-level intelligence.
This ingredient should allow computer systems to choreograph a parsimonious and modular representation of their environment, interrogate that representation, distort it by acts of imagination and finally answer "What if?" kind of questions. Examples are interventional questions: ΄What if I make it happen?‘ and retrospective or explanatory questions: ΄What if I had acted differently?‘ or ΄what if
my flight had not been late?‘ Such questions cannot be articulated, let alone answered by systems that operate in purely statistical
mode, as do most learning machines today."
--From "The Seven Tools of Causal Inference with Reflections on Machine Learning" by Judea Pearl
Causal reasoning is an integral part of data science and artificial intelligence. The goal of the course on Causal Inference and Learning is to introduce students to methodologies and algorithms for causal reasoning and connect various aspects of causal inference, including methods developed within computer science, statistics, and economics. The course will cover state-of-the-art research on causal reasoning and prepare students to conduct research in this area.
This is a seminar course. The goal of the course is to expose graduate students to state-of-the-art research on causal inference. The class project plays a central role in the course, and it should be taken as an opportunity to connect your research area of interest to the course topics.
Approximately one third of the course will be lecture-based using the following book by Judea Pearl, Madelyn Glymour and Nicholas Jewell: Causal Inference in Statistics: A Primer (Wiley Press 2016). The rest of the course will cover recent papers from the growing body of research on causal inference.
Homework - 15%
Paper summaries and discussion - 15%
Presentations - 20%
Course project - 50% (proposal, progress report, final presentation, final report)
CS 412 Introduction to Machine Learning or consent of the instructor.
We will be using Piazza for all course discussions and materials. Students registered for the course will be sent an enrollment email before the first day of class.
Philosophy of causality
Judea Pearl. The Seven Pillars of Causal Reasoning with Reflections on Machine Learning. Communications of the ACM. 2019.
Brenden M. Lake, Tomer D. Ullman, Joshua B. Tenenbaum, Samuel J. Gershman. Building Machines That Learn and Think Like People. 2016.
|9/3||Hypothesis testing and randomized controlled trials||
CIT Ch. 11 (book list at the end of table)
PTDS Ch. 18
|9/5||Statistical models: review||CISP Ch. 1||Professor|
|9/10||Structural causal models||CISP Ch. 1||Professor|
|9/12||Graphical models||CISP Ch. 2||Professor||HW 1 out|
|9/17||Interventions, adjustment formula, back-door criterion||CISP Ch. 3.1-3.3||Professor|
|9/19||Front-door criterion, covariate-specific effects, inverse probability weighing||CISP Ch. 3.4-3.6||Professor||HW 1 due 11:59pm|
|9/24||Mediation and causal inference in linear systems||CISP Ch. 3.7-3.8||Professor|
|9/26||Defining and computing counterfactuals||CISP Ch. 4.1-2.1||Professor||Project proposal due|
|10/1||Counterfactual probabilities, counterfactuals in linear systems||CISP Ch. 4.3||Professor|
|10/3||Counterfactuals: attribution, mediation, practical uses||CISP Ch. 4.4-4.5||Professor||HW 2 out|
Ziebart, Bignell, Dey. The principle of maximum causal entropy for estimating interacting processes. IEEE Transactions on Information Theory 2013.
Prof. Brian Ziebart
|10/10||Selection and transportability bias||
Bareinboim, Pearl. Causal inference and the data fusion problem. PNAS 2016.
Bareinboim, Tian, Pearl. Recovering from selection bias in causal and statistical inference. AAAI 2014. (best paper award)
Prof. Ali Tafti
|10/15||Causal discovery I||
CPS Ch. 5
Sridhar, Pujara, Getoor. "Scalable probabilistic causal structure discovery." IJCAI 2018. Code.
|10/17||Causal discovery II||
Chalupka, Perona, Eberhardt. Multi-level cause-effect systems. AISTATS 2016. Code.
Beckers, Eberhardt, Halpern. Approximate causal abstraction. UAI 2019.
|Aditi, Ragib||HW 2 due 11:59pm|
D'Amour. On multi-cause causal inference with unobserved confounding: Counterexamples, impossibility, and alternatives. AISTATS 2019.
Wang, Blei. The blessings of multiple causes. Arxiv 2018. Code.
Ogburn, VanderWeele. Causal diagrams for interference. Statistical science. 2014.
|10/29||Causal inference in networks I||
Bhattacharya, Malinsky, Shpitser. Causal inference under interference and network uncertainty. UAI 2019.
Arbour, Garant, Jensen. Inferring network effects in observational data. KDD 2016.
|10/31||Causal inference in networks II||
Shalizi, Thomas. Homophily and contagion are generically confounded in observational social network studies. Sociological Methods and Research, 40, 2011.
|11/5||Causal inference in social sciences||
Varian. Causal inference in economics and marketing, PNAS 2016.
Shmueli. To explain or to predict?, Stat. Science 2010.
Athey. Impact of machine learning on economics. Chapter in The Economics of AI: An Agenda. 2018.
|Professor||Progress report due 11:59pm|
|11/7||Causal inference in networks III||
Toulis, Kao. Estimation of causal peer influence effects. ICML 2013.
Eckles, Kizilcec, Bakshy. Estimating peer effects in networks with peer encouragement designs. PNAS 2016.
|11/12||Matching and propensity modeling||
Shahid, Zheleva. Counterfactual learning in networks: An empirical study of model dependence. AAAI-WHY 2019.
Stuart. Matching methods for causal inference: a review and look forward. Stat. Science 2010.
|11/14||Causal inference and NLP||
Wang, Culotta. When do words matter? Understanding the impact of lexical choice on audience perception using individual treatment effect estimation. AAAI 2019.
Landeiro, Tran, Culotta. Discovering and Controlling for Latent Confounds in Text Classification Using Adversarial Domain Adaptation. SDM 2019.
Prof. Aron Culotta
|11/19||Heterogeneous treatment effects||
Künzel, Sekhon, Bickel, Yu. Metalearners for estimating heterogeneous treatment effects using machine learning. PNAS 2019.
Tran, Zheleva. Learning triggers for heterogeneous treatment effects. AAAI 2019.
|11/21||Causal inference and machine learning||
Scholkopf, Janzing, Peters, Sgouritsa, Zhang, Mooij. On causal and anticausal inference. ICML 2012.
Peters, Janzing, Scholkopf. Identifying cause and effect on discrete data using Additive Noise Models. AISTAT 2010.
|11/26||Causal inference, reinforcement and transfer learning||
Lee, Bareinboim. Structural causal bandits: where to intervene. NIPS 2018.
Bengio, Deleu, Rahaman, Rosemary, Lachapelle, Bilaniuk, Goyal, Pal. A meta-transfer objective for learning to disentangle causal mechanisms. Arxiv 2019. Code.
|11/28||No class (Thanksgiving)|
|12/9||Finals week||Final project due 11:59pm|