Summary of Better Locally Private Sparse Estimation Given Multiple Samples Per User, by Yuheng Ma and Ke Jia and Hanfang Yang
Better Locally Private Sparse Estimation Given Multiple Samples Per User
by Yuheng Ma, Ke Jia, Hanfang Yang
First submitted to arxiv on: 8 Aug 2024
Categories
- Main: Machine Learning (stat.ML)
- Secondary: Machine Learning (cs.LG); Methodology (stat.ME)
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 paper investigates user-level locally differentially private sparse linear regression, which is challenging for high-dimensional data. The authors show that by eliminating the linear dependency of dimension d, the error upper bound can be reduced to O(s^*2 / nmε^2). A framework is proposed that selects candidate variables and then conducts estimation in a narrowed low-dimensional space, which can be extended to general sparse estimation problems with tight error bounds. Theoretical and empirical results demonstrate the superiority of the proposed methods. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary In this paper, researchers are trying to solve a problem where they want to do statistical analysis on big datasets while keeping individual data private. They found that previous methods didn’t work well for really high-dimensional data (think millions of features). So, they came up with a new way to do it called user-level locally differentially private sparse linear regression. This method is better than what they had before and can be used in many situations. |
Keywords
* Artificial intelligence * Linear regression
