This course explores the concept of group fairness with a focus on independence. The learning outcomes include understanding definitions such as gerrymandering, separation insufficiency, and increments of accuracy. The course teaches the skills of analyzing fairness in groups and drawing conclusions based on the concept of independence. The teaching method involves theoretical discussions and case studies. This course is intended for researchers, academics, and professionals interested in algorithmic fairness and group decision-making processes.
Overview
Syllabus
Introduction
Background
Definitions
gerrymandering
separation insufficiency
independence is unfair
increments of accuracy
conclusions
Taught by
ACM FAccT Conference
Related Courses
-
Bridging Machine Learning and Mechanism Design towards Algorithmic Fairness
-
Decoupled Classifiers for Group-Fair and Efficient Machine Learning
-
Fairness, Equality, and Power in Algorithmic Decision-Making
-
Toward a Theory of Race for Fairness in Machine Learning
-
Fairness, Rankings, and Behavioral Biases
-
Fairness and Accountability Design Needs for Algorithmic Support in High-Stakes Public Sector Decision-Making
