Position Paper: Bridging the Gap Between Machine Learning and Sensitivity Analysis
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912021630418944 |
|---|---|
| author | Scholbeck, Christian A. Moosbauer, Julia Casalicchio, Giuseppe Gupta, Hoshin Bischl, Bernd Heumann, Christian |
| author_facet | Scholbeck, Christian A. Moosbauer, Julia Casalicchio, Giuseppe Gupta, Hoshin Bischl, Bernd Heumann, Christian |
| contents | We argue that interpretations of machine learning (ML) models or the model-building process can be seen as a form of sensitivity analysis (SA), a general methodology used to explain complex systems in many fields such as environmental modeling, engineering, or economics. We address both researchers and practitioners, calling attention to the benefits of a unified SA-based view of explanations in ML and the necessity to fully credit related work. We bridge the gap between both fields by formally describing how (a) the ML process is a system suitable for SA, (b) how existing ML interpretation methods relate to this perspective, and (c) how other SA techniques could be applied to ML. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_13234 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Position Paper: Bridging the Gap Between Machine Learning and Sensitivity Analysis Scholbeck, Christian A. Moosbauer, Julia Casalicchio, Giuseppe Gupta, Hoshin Bischl, Bernd Heumann, Christian Machine Learning We argue that interpretations of machine learning (ML) models or the model-building process can be seen as a form of sensitivity analysis (SA), a general methodology used to explain complex systems in many fields such as environmental modeling, engineering, or economics. We address both researchers and practitioners, calling attention to the benefits of a unified SA-based view of explanations in ML and the necessity to fully credit related work. We bridge the gap between both fields by formally describing how (a) the ML process is a system suitable for SA, (b) how existing ML interpretation methods relate to this perspective, and (c) how other SA techniques could be applied to ML. |
| title | Position Paper: Bridging the Gap Between Machine Learning and Sensitivity Analysis |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2312.13234 |