Algorithmic Fairness From The Lens Of Causality And Information Theory
Offered By: Simons Institute via YouTube
Course Description
Overview
Syllabus
Intro
Motivation: Machine Learning in High-Stakes Applications
How to identify/explain sources of disparity in machine learning models?
Outline
Popular Definition: Statistical Parity
Conditional Dependence can sometimes falsely detect bias (misleading dependencies) even when a model is "causally" fair Example: Causally fair model
One causal measure that satisfies all desirable properties Theorem: Our proposed measure of non-exempt disparity, given by
Some intuition on our proposed measure from causality
Non-negative decomposition of total "causal" disparity Theorem 2 (pictorially illustrated)
Simulation: Four types of disparities present
Numerical Computation of Fundamental Limits on the Tradeoff 1.4
Reliable Machine Learning
Partial Information Decomposition + Causality
Taught by
Simons Institute
Related Courses
Towards an Ethical Digital Society: From Theory to PracticeNPTEL via Swayam Introduction to the Theory of Computing - Stanford
Stanford University via YouTube Fairness in Medical Algorithms - Threats and Opportunities
Open Data Science via YouTube Fairness in Representation Learning - Natalie Dullerud
Stanford University via YouTube Privacy Governance and Explainability in ML - AI
Strange Loop Conference via YouTube