Position: Rethinking Explainable Machine Learning as Applied Statistics

Sebastian Bordt, Eric Raidl, Ulrike Von Luxburg
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:81130-81142, 2025.

Abstract

In the rapidly growing literature on explanation algorithms, it often remains unclear what precisely these algorithms are for and how they should be used. 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. Among others, this implies that we must think carefully about the matter of interpretation, or how the explanations relate to intuitive questions that humans have about the world. The fact that this is scarcely being discussed in research papers is one of the main drawbacks of the current literature. Moving forward, the analogy between explainable machine learning and applied statistics provides a fruitful way for how research practices can be improved.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-bordt25b, title = {Position: Rethinking Explainable Machine Learning as Applied Statistics}, author = {Bordt, Sebastian and Raidl, Eric and Luxburg, Ulrike Von}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {81130--81142}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/bordt25b/bordt25b.pdf}, url = {https://proceedings.mlr.press/v267/bordt25b.html}, abstract = {In the rapidly growing literature on explanation algorithms, it often remains unclear what precisely these algorithms are for and how they should be used. 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. Among others, this implies that we must think carefully about the matter of interpretation, or how the explanations relate to intuitive questions that humans have about the world. The fact that this is scarcely being discussed in research papers is one of the main drawbacks of the current literature. Moving forward, the analogy between explainable machine learning and applied statistics provides a fruitful way for how research practices can be improved.} }
Endnote
%0 Conference Paper %T Position: Rethinking Explainable Machine Learning as Applied Statistics %A Sebastian Bordt %A Eric Raidl %A Ulrike Von Luxburg %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-bordt25b %I PMLR %P 81130--81142 %U https://proceedings.mlr.press/v267/bordt25b.html %V 267 %X In the rapidly growing literature on explanation algorithms, it often remains unclear what precisely these algorithms are for and how they should be used. 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. Among others, this implies that we must think carefully about the matter of interpretation, or how the explanations relate to intuitive questions that humans have about the world. The fact that this is scarcely being discussed in research papers is one of the main drawbacks of the current literature. Moving forward, the analogy between explainable machine learning and applied statistics provides a fruitful way for how research practices can be improved.
APA
Bordt, S., Raidl, E. & Luxburg, U.V.. (2025). Position: Rethinking Explainable Machine Learning as Applied Statistics. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:81130-81142 Available from https://proceedings.mlr.press/v267/bordt25b.html.

Related Material