可微社会选择中的开放问题：学习机制、决策与对齐
Open Problems in Differentiable Social Choice: Learning Mechanisms, Decisions, and Alignment
AI总结：
本文探讨了可微社会选择中的18个开放问题，研究如何将投票规则、机制和聚合过程作为可学习模型进行优化，揭示了经典公理在机器学习中的新应用。
摘要：
社会选择已成为现代机器学习系统的基础组件。从拍卖和资源分配到大生成模型的对齐，机器学习流水线越来越多地将异质偏好和激励聚合为集体决策。实际上，许多当代机器学习系统已经实现了社会选择机制，通常隐含且没有明确的规范性审视。本文综述了可微社会选择：一种新兴范式，将投票规则、机制和聚合过程作为可学习、可微的模型进行优化。我们综合了拍卖、决策聚合和偏好学习中的工作，展示了经典公理和不可能结果如何作为目标、约束和优化权衡重新出现。最后，我们通过18个开放问题定义了机器学习和社会选择理论交汇处的新研究议程。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
