Open Problems in Differentiable Social Choice: Learning Mechanisms, Decisions, and Alignment
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914341239914496 |
|---|---|
| author | An, Zhiyu Du, Wan |
| author_facet | An, Zhiyu Du, Wan |
| contents | Social choice has become a foundational component of modern machine learning systems. From auctions and resource allocation to the alignment of large generative models, machine learning pipelines increasingly aggregate heterogeneous preferences and incentives into collective decisions. In effect, many contemporary machine learning systems already implement social choice mechanisms, often implicitly and without explicit normative scrutiny.
This Review surveys differentiable social choice: an emerging paradigm that formulates voting rules, mechanisms, and aggregation procedures as learnable, differentiable models optimized from data. We synthesize work across auctions, decision aggregation, and preference learning, showing how classical axioms and impossibility results reappear as objectives, constraints, and optimization trade-offs. We conclude by identifying 18 open problems defining a new research agenda at the intersection of machine learning and social choice theory. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_03003 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Open Problems in Differentiable Social Choice: Learning Mechanisms, Decisions, and Alignment An, Zhiyu Du, Wan Artificial Intelligence Machine Learning Social choice has become a foundational component of modern machine learning systems. From auctions and resource allocation to the alignment of large generative models, machine learning pipelines increasingly aggregate heterogeneous preferences and incentives into collective decisions. In effect, many contemporary machine learning systems already implement social choice mechanisms, often implicitly and without explicit normative scrutiny. This Review surveys differentiable social choice: an emerging paradigm that formulates voting rules, mechanisms, and aggregation procedures as learnable, differentiable models optimized from data. We synthesize work across auctions, decision aggregation, and preference learning, showing how classical axioms and impossibility results reappear as objectives, constraints, and optimization trade-offs. We conclude by identifying 18 open problems defining a new research agenda at the intersection of machine learning and social choice theory. |
| title | Open Problems in Differentiable Social Choice: Learning Mechanisms, Decisions, and Alignment |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2602.03003 |