Causal Learning Reading Group (Summer 2023)

Generated using Crayon.AI with prompt 'causal learning'


1. Description

1.1 Objectives

This reading group will cover the basics of causal learning and some advanced topics and applications. The first half of the reading group will include sessions led by Anshuman and Hannah to cover basic concepts like causal structural models and do-calculus, followed by more advanced topics and applications in fields like machine learning.

The objectives of this reading group are:

  1. Provide participants with a solid understanding of causal theory and highlight the limitations of relying solely on statistics.
  2. Familiarize participants with do-calculus, interventions, and methods for interpreting and interacting with causal graphs.
  3. Enable participants to confidently read and comprehend causality-driven approaches, particularly in the context of machine learning applications.

1.2 Prerequisites

This reading group will begin with a comprehensive introduction to causal learning, gradually progressing to advanced topics and applications in machine learning. Participants are only required to have a basic foundation in mathematics, including probability and algebra. Additionally, a basic understanding of machine learning concepts would be beneficial.

2. Schedule

Schedule with topics can be found on this page

3. Readings

For a list of useful resources and papers that we discussed in the reading group, please refer to this page.