Summary of Optimized Tradeoffs For Private Prediction with Majority Ensembling, by Shuli Jiang et al.
Optimized Tradeoffs for Private Prediction with Majority Ensembling
by Shuli Jiang, Qiuyi, Zhang, Gauri Joshi
First submitted to arxiv on: 27 Nov 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 This research paper proposes a novel algorithm called Data-dependent Randomized Response Majority (DaRRM) to solve the problem of computing an (m, )-differentially private majority of K (, )-differentially private algorithms for 1 m K and 1 > . The algorithm is parameterized by a data-dependent noise function , which enables efficient utility optimization over the class of all private algorithms. The authors show that maximizing the utility of an (m, )-private majority algorithm can be computed tractably through an optimization problem for any m K. They also demonstrate the strong empirical effectiveness of DaRRM in ensembling labels for private prediction from private teachers in image classification. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper solves a classic problem in privacy prediction by introducing the Data-dependent Randomized Response Majority (DaRRM) algorithm. The researchers want to know if standard methods like subsampling or randomized response provide the best balance between privacy and usefulness. They create DaRRM, which uses a special noise function that depends on the data. This allows them to optimize the balance between privacy and usefulness much better than before. The results show that DaRRM can be up to twice as good at balancing privacy and usefulness compared to common methods. |
Keywords
» Artificial intelligence » Image classification » Optimization
