Summary of Provably Accurate Shapley Value Estimation Via Leverage Score Sampling, by Christopher Musco and R. Teal Witter
Provably Accurate Shapley Value Estimation via Leverage Score Sampling
by Christopher Musco, R. Teal Witter
First submitted to arxiv on: 2 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI)
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 proposes a new method for computing Shapley values in explainable machine learning, which are used to attribute model predictions to specific input features. The existing algorithm, Kernel SHAP, is widely used but lacks strong non-asymptotic complexity guarantees. To address this issue, the authors introduce Leverage SHAP, a lightweight modification of Kernel SHAP that provides provably accurate Shapley value estimates with just O(nlogn) model evaluations. This approach takes advantage of a connection between Shapley value estimation and agnostic active learning by employing leverage score sampling. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper helps explainable machine learning models attribute their predictions to specific input features, which is important for understanding how they work. The new method, Leverage SHAP, is faster and more accurate than the old one, Kernel SHAP. This makes it useful for big models with many features. |
Keywords
» Artificial intelligence » Active learning » Machine learning
