Explore a 20-minute conference talk from the FAccT 2021 virtual event that introduces a statistical test for probabilistic fairness. Delve into the research presented by B. Taskesen, J. Blanchet, D. Kuhn, and V. Nguyen, which addresses the critical issue of fairness in machine learning algorithms. Learn about their innovative approach to detecting and quantifying bias in probabilistic classifiers, and gain insights into how this test can be applied to improve fairness in various AI applications. Understand the implications of this research for developing more equitable and just machine learning systems across different domains.
Overview
Syllabus
A Statistical Test for Probabilistic Fairness
Taught by
ACM FAccT Conference
Related Courses
-
Bridging Machine Learning and Mechanism Design towards Algorithmic Fairness
-
Re-imagining Algorithmic Fairness in India and Beyond
-
Fairness Methods
-
Detecting Discriminatory Risk through Data Annotation Based on Bayesian Inferences
-
Evaluating Fairness of Machine Learning Models Under Uncertain and Incomplete Information
-
I Agree with the Decision, but They Didn't Deserve This - Future Developers' Perception of Fairness
