Summary of General Bounds on the Quality Of Bayesian Coresets, by Trevor Campbell
General bounds on the quality of Bayesian coresets
by Trevor Campbell
First submitted to arxiv on: 20 May 2024
Categories
- Main: Machine Learning (stat.ML)
- Secondary: 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 Bayesian coresets speed up posterior inference by approximating log-likelihood functions using a weighted subset of data. This paper presents general bounds on the Kullback-Leibler divergence of coreset approximations, applying to various models without strong assumptions. The bounds are used to analyze performance and limitations of construction methods, including importance sampling and subsample-optimize approaches. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This study shows how Bayesian coresets can speed up posterior inference by using a small subset of data. It gives general rules for how well this works, applying to many types of models without needing strong assumptions. This helps explain why some methods work better than others and provides a new way to analyze the performance of these methods. |
Keywords
» Artificial intelligence » Inference » Log likelihood
