Summary of Uncertainty Quantification by Block Bootstrap For Differentially Private Stochastic Gradient Descent, By Holger Dette et al.
Uncertainty quantification by block bootstrap for differentially private stochastic gradient descent
by Holger Dette, Carina Graw
First submitted to arxiv on: 21 May 2024
Categories
- Main: Machine Learning (stat.ML)
- Secondary: Cryptography and Security (cs.CR); Machine Learning (cs.LG); Statistics Theory (math.ST); Computation (stat.CO)
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 proposes a novel block bootstrap method for Stochastic Gradient Descent (SGD) under local differential privacy, allowing for uncertainty quantification without requiring multiple queries to private data. The approach is computationally tractable and does not adjust the privacy budget. This method can be easily implemented and applies to a broad range of estimation problems. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper develops a new way to use a popular machine learning tool called Stochastic Gradient Descent while keeping people’s personal information safe. Usually, these two ideas are hard to combine because they require different types of calculations. The researchers found a way to do both at the same time, making it easier to understand how accurate their predictions are. |
Keywords
» Artificial intelligence » Machine learning » Stochastic gradient descent
