Summary of Auditing Fairness Under Unobserved Confounding, by Yewon Byun et al.
Auditing Fairness under Unobserved Confounding
by Yewon Byun, Dylan Sam, Michael Oberst, Zachary C. Lipton, Bryan Wilder
First submitted to arxiv on: 18 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computers and Society (cs.CY); Methodology (stat.ME); Machine Learning (stat.ML)
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 proposed paper introduces a novel approach to estimating fairness in decision-making systems without relying on strong assumptions. The method is particularly useful when dealing with unobservable causal quantities that cannot be directly estimated, such as risk-based notions of fairness. By leveraging prior data and relaxing the assumption of observing all relevant risk factors, the authors show that meaningful bounds can still be computed for high-risk individuals. This allows for principled auditing of unfair outcomes in existing decision-making systems. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine you’re trying to figure out if a new treatment is being given equally to people who need it most. But how do you know what “most” means? The problem is that we can’t always measure things like risk directly, and even when we try, there might be other factors at play that we don’t see. This paper shows that, surprisingly, we can still get a good idea of whether people are getting the treatment they need by looking at what happened before any decisions were made. |
