Summary of Privacy-preserving Data Release Leveraging Optimal Transport and Particle Gradient Descent, by Konstantin Donhauser and Javier Abad and Neha Hulkund and Fanny Yang
Privacy-preserving data release leveraging optimal transport and particle gradient descent
by Konstantin Donhauser, Javier Abad, Neha Hulkund, Fanny Yang
First submitted to arxiv on: 31 Jan 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 A novel approach to differentially private data synthesis of protected tabular datasets is introduced in this paper, with potential applications in sensitive domains such as healthcare and government. The authors propose PrivPGD, a generation method that leverages optimal transport and particle gradient descent tools, outperforming existing methods on various datasets while being highly scalable and adaptable to additional constraints. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates a new way to keep private data safe while still using it for important tasks. Imagine you have super sensitive information about people’s health or government records. The authors want to make sure this info is protected while still allowing scientists to use it to help people. They created a new method called PrivPGD that does just that, and it works really well on lots of different data sets. |
Keywords
* Artificial intelligence * Gradient descent
