Completed
Intro
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Algorithmic Fairness From The Lens Of Causality And Information Theory
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Motivation: Machine Learning in High-Stakes Applications
- 3 How to identify/explain sources of disparity in machine learning models?
- 4 Outline
- 5 Popular Definition: Statistical Parity
- 6 Conditional Dependence can sometimes falsely detect bias (misleading dependencies) even when a model is "causally" fair Example: Causally fair model
- 7 One causal measure that satisfies all desirable properties Theorem: Our proposed measure of non-exempt disparity, given by
- 8 Some intuition on our proposed measure from causality
- 9 Non-negative decomposition of total "causal" disparity Theorem 2 (pictorially illustrated)
- 10 Simulation: Four types of disparities present
- 11 Numerical Computation of Fundamental Limits on the Tradeoff 1.4
- 12 Reliable Machine Learning
- 13 Partial Information Decomposition + Causality
