Summary of A Practical Theory Of Generalization in Selectivity Learning, by Peizhi Wu et al.
A Practical Theory of Generalization in Selectivity Learning
by Peizhi Wu, Haoshu Xu, Ryan Marcus, Zachary G. Ives
First submitted to arxiv on: 11 Sep 2024
Categories
- Main: Machine Learning (stat.ML)
- Secondary: Databases (cs.DB); 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 The paper presents a theoretical study on query-driven machine learning models for estimating query selectivities. It bridges the gap between practical solutions and state-of-the-art theory based on the PAC learning framework. The authors demonstrate that signed measure-based selectivity predictors are learnable, which relaxes the reliance on probability measures in SOTA theory. They also establish favorable out-of-distribution generalization error bounds for these predictors under mild assumptions. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper explores how to improve query-driven machine learning models for estimating query selectivities. By showing that signed measure-based predicters are learnable and have good performance when the data is different from what was used to train them, it helps us better understand these models and how they work. |
Keywords
» Artificial intelligence » Generalization » Machine learning » Probability
