Summary of Differentially Private High Dimensional Bandits, by Apurv Shukla
Differentially Private High Dimensional Bandits
by Apurv Shukla
First submitted to arxiv on: 6 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR); Systems and Control (eess.SY); Optimization and Control (math.OC); Machine Learning (stat.ML)
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 tackle a high-dimensional linear bandit problem with a sparse parameter vector while ensuring user privacy. They propose PrivateLASSO, an algorithm that balances utility and privacy in both central and local differential privacy models. The algorithm consists of two components: a privacy mechanism based on hard-thresholding and an episodic thresholding rule to identify the support of the parameter θ. The authors prove lower bounds for private algorithms and establish guarantees for PrivateLASSO’s performance under standard assumptions. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper explores how to make smart decisions in situations where there are many variables involved, while also keeping user information safe. It presents a new algorithm called PrivateLASSO that balances making good choices with protecting privacy. The algorithm works by using two techniques: one for maintaining privacy and another for figuring out which variables are most important. |
