Causal Foundations for Pragmatic Data Science

A key goal of scientific discovery is the acquisition of knowledge that is practically useful for societal endeavors, such as the development of medicine or the design of fruitful economic policies. In this thesis, I place front and center the role that scientific models play in the process of decision-making, emphasizing the importance of causal models in science, i.e., models which describe the possible effects of actions upon a system. The work contained explores central topics in this domain, including causal discovery (learning causal models from data), causal representation learning (learning how to coarse-grain observations into causally sensible “macro-variables”), and end-to-end causal inference (the interplay between causal discovery and downstream decision-making).

Name thesis:degree_name

Doctoral

Department dc:contributor.department

Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science

Grantor dc:publisher

Massachusetts Institute of Technology

Year dc:date.issued

2025

Author dc:creator

• Squires, Chandler

Advisors dc:contributor.advisor

• Uhler, Caroline
• Sontag, David

Statement dc:rights

• In Copyright - Educational Use Permitted
• Copyright retained by author(s)

Licence dc:rights.uri

• https://rightsstatements.org/page/InC-EDU/1.0/

Handle dc:identifier.uri

https://hdl.handle.net/1721.1/158952

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/158952