Research map / Learning theory and algorithms / Sample complexity
Adalina: Adaptive Linear Approximation for the Shapley Value and Beyond
Weida Li, Yaoliang Yu, Bryan Kian Hsiang Low
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use paired sampling when the utility does not change sign | gamma-adjusted linear estimators · tree-model utilities on OpenML datasets | relative approximation error | Improved |
| replace SHAP-IQ sampling distribution with the optimal one | SHAP-IQ · tree-model utilities on OpenML datasets | relative approximation error | Improved |
| add adaptive estimate of the shift gamma (Adalina) instead of fixed gamma | linear semi-value estimator · Beta Shapley and weighted Banzhaf semi-values | relative approximation error | Mixed |
Closest papers by meaning
- DU-Shapley: A Shapley Value Proxy for Efficient Dataset Valuation (NeurIPS 2024 · similarity 0.87)
- A Unified Framework for Provably Efficient Algorithms to Estimate Shapley Values (NeurIPS 2025 · similarity 0.86)
- One Sample Fits All: Approximating All Probabilistic Values Simultaneously and Efficiently (NeurIPS 2024 · similarity 0.86)
- Regression-adjusted Monte Carlo Estimators for Shapley Values and Probabilistic Values (NeurIPS 2025 · similarity 0.86)
- Provably Accurate Shapley Value Estimation via Leverage Score Sampling (ICLR 2025 · similarity 0.84)
- Amortized Linear-time Exact Shapley Value for Product-Kernel Methods (NeurIPS 2026 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
