Summary of Private Wasserstein Distance, by Wenqian Li et al.
Private Wasserstein Distance
by Wenqian Li, Yan Pang
First submitted to arxiv on: 10 Apr 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 paper presents a novel approach called TriangleWad that efficiently computes the Wasserstein distance between datasets stored across different entities while ensuring complete data privacy. By leveraging the triangular properties within the Wasserstein space, TriangleWad combines high estimation accuracy with robust resistance to potential attacks. The authors demonstrate its superior performance through extensive experiments involving image and text data, highlighting its potential for real-world applications. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about a new way to measure how different two sets of data are without actually sharing the data itself. This is important because sometimes we can’t share our data directly. The current methods for doing this, like Differential Privacy and Federated Optimization, are not perfect. They might be too inaccurate or not secure enough. So, researchers developed a new method called TriangleWad that uses special properties of math to quickly calculate how different the data is without seeing it. This helps keep the data private while still giving us good results. |
Keywords
* Artificial intelligence * Optimization
