Summary of Adaptive Batch Size For Privately Finding Second-order Stationary Points, by Daogao Liu et al.
Adaptive Batch Size for Privately Finding Second-Order Stationary Points
by Daogao Liu, Kunal Talwar
First submitted to arxiv on: 10 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR); Data Structures and Algorithms (cs.DS); 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 This paper investigates the challenges of finding a second-order stationary point (SOSP) under differential privacy constraints. While Ganesh et al. claimed to have found an SOSP with a certain bound, recent analysis revealed issues with their approach. The authors propose a new method using adaptive batch sizes and the binary tree mechanism, which corrects the previous mistakes and achieves better results for privately finding an SOSP. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper looks at how hard it is to find something in a special way when you have to keep data private. Some people thought they found a certain kind of point, but others showed that their method wasn’t perfect. The researchers are working on a new way to do this that’s better and more accurate. |
