Summary of To Pool or Not to Pool: Analyzing the Regularizing Effects Of Group-fair Training on Shared Models, by Cyrus Cousins et al.
To Pool or Not To Pool: Analyzing the Regularizing Effects of Group-Fair Training on Shared Models
by Cyrus Cousins, I. Elizabeth Kumar, Suresh Venkatasubramanian
First submitted to arxiv on: 29 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computers and Society (cs.CY)
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 A new paper in fair machine learning tackles performance disparities between groups by deriving group-specific bounds on the generalization error. The approach focuses on welfare-centric fairness and leverages the larger sample size of the majority group. By considering Rademacher averages over a restricted hypothesis class, the method improves upon naive methods, especially for smaller group sizes. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In a machine learning paper, researchers aim to reduce performance disparities between groups by developing fair models that don’t favor one group over another. They do this by creating special math formulas called “group-specific bounds” that help machines learn better from bigger groups. This way, everyone gets a fair chance! |
Keywords
* Artificial intelligence * Generalization * Machine learning
