Loading Now

Summary of Algorithmic Fairness in Performative Policy Learning: Escaping the Impossibility Of Group Fairness, by Seamus Somerstep et al.


Algorithmic Fairness in Performative Policy Learning: Escaping the Impossibility of Group Fairness

by Seamus Somerstep, Ya’acov Ritov, Yuekai Sun

First submitted to arxiv on: 30 May 2024

Categories

  • Main: Machine Learning (stat.ML)
  • Secondary: Computers and Society (cs.CY); Machine Learning (cs.LG)

     Abstract of paper      PDF of paper


GrooveSquid.com Paper Summaries

GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!

Summary difficulty Written by Summary
High Paper authors High Difficulty Summary
Read the original abstract here
Medium GrooveSquid.com (original content) Medium Difficulty Summary
The paper develops algorithmic fairness practices that exploit performativity to achieve stronger group fairness guarantees in social classification problems. This involves leveraging the policymaker’s ability to steer the population to remedy inequities in the long term. The approach resolves incompatibilities between conflicting group fairness definitions and outperforms traditional methods.
Low GrooveSquid.com (original content) Low Difficulty Summary
The paper helps make predictive models fairer by using something called performativity. Performativity is when a model affects how people behave, which can be good or bad. In this case, the researchers use performativity to make sure certain groups are treated fairly. They do this by letting policymakers control the population to fix inequalities over time. This approach makes fairness more achievable and fixes problems between different definitions of fairness.

Keywords

» Artificial intelligence  » Classification