Summary of Locally Private Estimation with Public Features, by Yuheng Ma and Ke Jia and Hanfang Yang
Locally Private Estimation with Public Features
by Yuheng Ma, Ke Jia, Hanfang Yang
First submitted to arxiv on: 22 May 2024
Categories
- Main: Machine Learning (stat.ML)
- Secondary: Cryptography and Security (cs.CR); Machine Learning (cs.LG)
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 introduces the concept of locally differentially private (LDP) learning with public features, defining semi-feature LDP where some features are publicly available while others require protection. The authors demonstrate that the mini-max convergence rate for non-parametric regression is reduced under semi-feature LDP compared to classical LDP. They propose HistOfTree, an estimator that leverages information from both public and private features, achieving optimal convergence rates theoretically and superior performance empirically on synthetic and real data. |
Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper studies a new type of machine learning problem where some features are publicly available while others need to be kept private. The researchers develop special algorithms for this situation, called semi-feature LDP, which can accurately predict outcomes based on both public and private information. They also design a new estimator called HistOfTree that performs well in various scenarios. |
Keywords
» Artificial intelligence » Machine learning » Regression