A Tutorial on Fairness in Machine Learning

This post will be the first post on the series. The purpose of this post is to: 1. give a quick but relatively comprehensive survey of Fair ML. 2. provide references and resources to readers at all levels who are interested in Fair ML. The content is based on: the tutorial on fairness given by Solon Bacrocas and Moritz Hardt at NIPS2017, day1 and day4 from CS 294: Fairness in Machine Learning taught by Moritz Hardt at UC Berkeley and my own understanding of fairness literatures. I highly encourage interested readers to check out the linked NIPS tutorial and the course website. The current post consists of six parts: Introduction; Motivations; Causes of bias in ML; Definitions of fairness including formulation, motivations, example, and flaws, Algorithms used to achieve those fairness definitions, and Summary