mlsanityData to 14 Oct 2026

Shapley Curves: A Smoothing Perspective

arXiv 2211.13289 ↗First posted 23 Nov 2022stat.ML cs.LG stat.MEcited by 2

Not on the map. Why?

Abstract (arXiv)

This paper fills the limited statistical understanding of Shapley values as a variable importance measure from a nonparametric (or smoothing) perspective. We introduce population-level textitShapley curves to measure the true variable importance, determined by the conditional expectation function and the distribution of covariates. Having defined the estimand, we derive minimax convergence rates and asymptotic normality under general conditions for the two leading estimation strategies. For finite sample inference, we propose a novel version of the wild bootstrap procedure tailored for capturing lower-order terms in the estimation of Shapley curves. Numerical studies confirm our theoretical findings, and an empirical application analyzes the determining factors of vehicle prices.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 24 of its 70 references that are in the map. First posted on arXiv 23 Nov 2022.

Builds on

24 of 70 references.

References · 24

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2017Nonparametric regression using deep neural networks with ReLU activation functioncited by 433
  3. 2019The many Shapley values for model explanationcited by 344
  4. 2020Explaining by Removing: A Unified Framework for Model Explanationcited by 218
  5. 2019Explaining individual predictions when features are dependent: More accurate approximations to Shapley valuescited by 208
  6. 2020Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regressioncited by 154
  7. 2021FastSHAP: Real-Time Shapley Value Estimationcited by 125
  8. 2020Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challengescited by 120
  9. 2022Algorithms to estimate Shapley value feature attributionscited by 115
  10. 2020Shapley explainability on the data manifoldcited by 88
  11. 2014Consistency of random forestscited by 85
  12. 2020Efficient nonparametric statistical inference on population feature importance using Shapley valuescited by 61
12 more
  1. 2020A Multilinear Sampling Algorithm to Estimate Shapley Valuescited by 33
  2. 2021SHAFF: Fast and consistent SHApley eFfect estimates via random Forestscited by 22
  3. 2022Unifying local and global model explanations by functional decomposition of low dimensional structurescited by 18
  4. 2020Trees, forests, and impurity-based variable importancecited by 16
  5. 2021Decorrelated Variable Importancecited by 13
  6. 2021MDA for random forests: inconsistency, and a practical solution via the Sobol-MDAcited by 10
  7. 2021Explaining predictive models using Shapley values and non-parametric vine copulascited by 9
  8. 2020Random Planted Forest: a directly interpretable tree ensemblecited by 5
  9. 2020Explainable AI for a No-Teardown Vehicle Component Cost Estimation: A Top-Down Approachcited by 3
  10. 2014Marginal integration for nonparametric causal inferencecited by 2
  11. 2021Inferring feature importance with uncertainties in high-dimensional datacited by 2
  12. 2022A Data-driven Case-based Reasoning in Bankruptcy Predictioncited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Interpretable Tabular Foundation Models via In-Context Kernel Regressioncited by 4
  2. 2026Statistical Inference and Learning for Shapley Additive Explanations (SHAP)cited by 1