Omitted Labels Induce Nontransitive Paradoxes in Causality
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908344124440576 |
|---|---|
| author | Mazaheri, Bijan Jain, Siddharth Cook, Matthew Bruck, Jehoshua |
| author_facet | Mazaheri, Bijan Jain, Siddharth Cook, Matthew Bruck, Jehoshua |
| contents | We explore "omitted label contexts," in which training data is limited to a subset of the possible labels. This setting is standard among specialized human experts or specific, focused studies. By studying Simpson's paradox, we observe that ``correct'' adjustments sometimes require non-exchangeable treatment and control groups. A generalization of Simpson's paradox leads us to study networks of conclusions drawn from different contexts, within which a paradox of nontransitivity arises. We prove that the space of possible nontransitive structures in these networks exactly corresponds to structures that form from aggregating ranked-choice votes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_06840 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Omitted Labels Induce Nontransitive Paradoxes in Causality Mazaheri, Bijan Jain, Siddharth Cook, Matthew Bruck, Jehoshua Machine Learning Artificial Intelligence Information Theory Social and Information Networks Methodology We explore "omitted label contexts," in which training data is limited to a subset of the possible labels. This setting is standard among specialized human experts or specific, focused studies. By studying Simpson's paradox, we observe that ``correct'' adjustments sometimes require non-exchangeable treatment and control groups. A generalization of Simpson's paradox leads us to study networks of conclusions drawn from different contexts, within which a paradox of nontransitivity arises. We prove that the space of possible nontransitive structures in these networks exactly corresponds to structures that form from aggregating ranked-choice votes. |
| title | Omitted Labels Induce Nontransitive Paradoxes in Causality |
| topic | Machine Learning Artificial Intelligence Information Theory Social and Information Networks Methodology |
| url | https://arxiv.org/abs/2311.06840 |