Position: Rethinking Explainable Machine Learning as Applied Statistics
Authors: Sebastian Bordt, Eric Raidl, Ulrike Von Luxburg
ICML 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | In this position paper, we argue for a novel and pragmatic perspective: Explainable machine learning needs to recognize its parallels with applied statistics. Concretely, explanations are statistics of high-dimensional functions, and we should think about them analogously to traditional statistical quantities. |
| Researcher Affiliation | Academia | 1University of T ubingen, T ubingen AI Center, Germany 2University of T ubingen, Germany. Correspondence to: Sebastian Bordt <EMAIL>. |
| Pseudocode | No | The paper discusses various algorithms conceptually, such as SHAP and LIME, and presents the mathematical formula for SHAP values, but it does not contain any structured pseudocode or algorithm blocks for its own methodology. |
| Open Source Code | No | The paper is a position paper arguing a conceptual framework and does not describe any specific methodology that would require source code release. |
| Open Datasets | No | The paper is a position paper and does not describe any empirical studies or experiments that would involve the use or release of datasets. It mentions 'benchmark datasets' in a conceptual discussion about evaluation, but not as data used in this work. |
| Dataset Splits | No | The paper is a theoretical position paper and does not involve experimental evaluation with datasets, hence no dataset split information is provided. |
| Hardware Specification | No | The paper is a theoretical position paper and does not describe any experimental setup or hardware used for computation. |
| Software Dependencies | No | The paper is a theoretical position paper and does not describe any experimental setup or software dependencies. |
| Experiment Setup | No | The paper is a theoretical position paper and does not describe any experimental setup, hyperparameters, or training configurations. |