Summary of Data Deletion For Linear Regression with Noisy Sgd, by Zhangjie Xia et al.
Data Deletion for Linear Regression with Noisy SGD
by Zhangjie Xia, Chi-Hua Wang, Guang Cheng
First submitted to arxiv on: 12 Oct 2024
Categories
- Main: Machine Learning (stat.ML)
- Secondary: 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 This paper addresses the challenge of shrinking training dataset sizes while maintaining performance in machine learning models. The authors propose the “perfect deleted point” problem, where they aim to find the optimal points to delete from a dataset without significantly impacting model accuracy or introducing underfitting issues. They develop an algorithm based on signal-to-noise ratio and demonstrate its effectiveness using a synthetic dataset. Additionally, they analyze the consequences of data deletion on training performance and privacy budget. The study highlights the importance of data deletion and underscores the need for further research in this area. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about finding ways to make machine learning models more efficient by reducing the amount of data used to train them. The authors want to know which parts of the dataset can be safely removed without affecting how well the model works. They develop a new method that helps with this problem and test it on some sample data. This research shows why it’s important to delete unnecessary data and suggests we need more studies in this area. |
Keywords
» Artificial intelligence » Machine learning » Underfitting
