Summary of Bounding the Excess Risk For Linear Models Trained on Marginal-preserving, Differentially-private, Synthetic Data, by Yvonne Zhou et al.
Bounding the Excess Risk for Linear Models Trained on Marginal-Preserving, Differentially-Private, Synthetic Data
by Yvonne Zhou, Mingyu Liang, Ivan Brugere, Dana Dachman-Soled, Danial Dervovic, Antigoni Polychroniadou, Min Wu
First submitted to arxiv on: 6 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR)
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 In this paper, researchers explore ways to prevent machine learning (ML) models from revealing private information about individuals who contributed to their training datasets. One approach involves using differentially-private (DP), synthetic training data instead of real data. The authors focus on preserving the statistical properties of the original distribution in these synthetic data and derive upper and lower bounds on the excess empirical risk of linear models trained on this data. Theoretical results are supported by extensive experimentation. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine a world where machine learning models don’t reveal our personal secrets! This paper shows how to make that happen. By using fake training data instead of real data, we can hide private information about individuals who contributed to the model’s training. The authors figure out how to keep the fake data looking like the real thing and test their ideas with lots of examples. |
Keywords
* Artificial intelligence * Machine learning * Synthetic data
