Research map / Probabilistic and scientific modeling / Bayesian optimization
HyperSHAP: Shapley Values and Interactions for Explaining Hyperparameter Optimization
Marcel Wever, Maximilian Muschalik, Fabian Fumagalli, Marius Lindauer
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 Tunability game instead of Ablation game for explaining an optimized configuration (ablation) | HyperSHAP · PD1 lm1b transformer | explanation of hyperparameter importance | Improved |
| select top-2 hyperparameters via HyperSHAP instead of fANOVA before HPO | HPO run on two hyperparameters · lcbench (two datasets) | anytime performance | Improved |
| use Tunability game instead of Sensitivity game to pick hyperparameters to tune (ablation) | HyperSHAP · lcbench (two datasets) | anytime performance | Improved |
| raise Shapley interaction explanation order up to 3 (ablation) | HyperSHAP · HPO benchmarks | faithfulness (R2): R2 ≈ 1 at order 3 | Improved |
| raise explanation order beyond third (ablation) | HyperSHAP · HPO benchmarks | faithfulness (R2) | No clear effect |
| use Optimizer Bias game to detect optimizer that tunes hyperparameters independently | HyperSHAP · lcbench dataset 3945 | bias detection | Improved |
| use Optimizer Bias game to detect optimizer that skips weight decay tuning | HyperSHAP · lcbench dataset 3945 | bias detection | Improved |
Closest papers by meaning
- KernelSHAP-IQ: Weighted Least Square Optimization for Shapley Interactions (ICML 2024 · similarity 0.87)
- Interactive Hyperparameter Optimization in Multi-Objective Problems via Preference Learning (AAAI 2024 · similarity 0.87)
- shapiq: Shapley Interactions for Machine Learning (NeurIPS 2024 · similarity 0.86)
- OperatorSHAP: Fast and Accurate Shapley Value Estimation for Neural Operators (NeurIPS 2026 · similarity 0.85)
- Provably Accurate Shapley Value Estimation via Leverage Score Sampling (ICLR 2025 · similarity 0.85)
- Unlocking the Game: Estimating Games in Möbius Representation for Explanation and High-Order Interaction Detection (AAAI 2025 · similarity 0.85)
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.
