Summary of On the Impact Of Output Perturbation on Fairness in Binary Linear Classification, by Vitalii Emelianov et al.
On the Impact of Output Perturbation on Fairness in Binary Linear Classification
by Vitalii Emelianov, Michaël Perrot
First submitted to arxiv on: 5 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 This research paper investigates how differential privacy interacts with both individual and group fairness in binary linear classification. The study focuses on the output perturbation mechanism, a classic approach in privacy-preserving machine learning. The authors derive high-probability bounds on the level of individual and group fairness that the perturbed models can achieve compared to the original model. Specifically, they prove that the impact of output perturbation on individual fairness is bounded but grows with the dimension of the model, while for group fairness, it is determined by the distribution of angular margins. This research provides insights into the trade-off between privacy and fairness in machine learning. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at how making data private affects whether a computer program treats people fairly. The researchers looked at a special way to make sure personal information isn’t shared, called output perturbation. They wanted to know how this makes the program fairer or less fair compared to when it’s not trying to keep things private. They found out that making things private can affect fairness in different ways depending on the size of the data and who it’s being used for. |
Keywords
* Artificial intelligence * Classification * Machine learning * Probability
