Methods and Open Problems in Differentiable Social Choice: Learning Mechanisms, Decisions, and Alignment

• URL: http://arxiv.org/abs/2602.03003v2
• Date: Thu, 05 Feb 2026 19:13:00 GMT
• Title: Methods and Open Problems in Differentiable Social Choice: Learning Mechanisms, Decisions, and Alignment
• Authors: Zhiyu An, Wan Du,
• Abstract summary: Social choice is no longer a peripheral concern of political theory or economics.<n>This Review surveys differentiable social choice: an emerging paradigm that formulates voting rules, mechanisms, and aggregation procedures as learnable, differentiable models optimized from data.
• Score: 7.764532811300023
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Social choice is no longer a peripheral concern of political theory or economics-it has become a foundational component of modern machine learning systems. From auctions and resource allocation to federated learning, participatory governance, and the alignment of large language models, machine learning pipelines increasingly aggregate heterogeneous preferences, incentives, and judgments 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, voting, budgeting, liquid democracy, decentralized aggregation, and inverse mechanism learning, showing how classical axioms and impossibility results reappear as objectives, constraints, and optimization trade-offs. We conclude by identifying 36 open problems defining a new research agenda at the intersection of machine learning, economics, and social choice theory.

Related papers

• Representative Social Choice: From Learning Theory to AI Alignment [1.5831647807014813]
  In representative social choice, the population is represented by a finite sample of individual-issue pairs.<n>We show that many of the deepest questions in representative social choice can be formulated as statistical learning problems.<n>We formulate further axioms for representative social choice, and prove Arrow-like impossibility theorems with new tools of analysis.
  arXiv  Detail & Related papers  (2024-10-31T14:07:26Z)
• Learning from Evolution: Improving Collective Decision-Making Mechanisms using Insights from Evolutionary Robotics [2.1756081703276]
  Collective decision-making enables multi-robot systems to act autonomously in real-world environments. Recent work has shown that more efficient collective decision-making mechanisms can be generated using methods from evolutionary computation. We analyze evolved collective decision-making mechanisms in detail and hand-code two new decision-making mechanisms based on the insights gained.
  arXiv  Detail & Related papers  (2024-05-03T14:37:17Z)
• Ecosystem-level Analysis of Deployed Machine Learning Reveals Homogeneous Outcomes [72.13373216644021]
  We study the societal impact of machine learning by considering the collection of models that are deployed in a given context. We find deployed machine learning is prone to systemic failure, meaning some users are exclusively misclassified by all models available. These examples demonstrate ecosystem-level analysis has unique strengths for characterizing the societal impact of machine learning.
  arXiv  Detail & Related papers  (2023-07-12T01:11:52Z)
• Social Diversity Reduces the Complexity and Cost of Fostering Fairness [63.70639083665108]
  We investigate the effects of interference mechanisms which assume incomplete information and flexible standards of fairness. We quantify the role of diversity and show how it reduces the need for information gathering. Our results indicate that diversity changes and opens up novel mechanisms available to institutions wishing to promote fairness.
  arXiv  Detail & Related papers  (2022-11-18T21:58:35Z)
• Causal Fairness Analysis [68.12191782657437]
  We introduce a framework for understanding, modeling, and possibly solving issues of fairness in decision-making settings. The main insight of our approach will be to link the quantification of the disparities present on the observed data with the underlying, and often unobserved, collection of causal mechanisms. Our effort culminates in the Fairness Map, which is the first systematic attempt to organize and explain the relationship between different criteria found in the literature.
  arXiv  Detail & Related papers  (2022-07-23T01:06:34Z)
• Individual Explanations in Machine Learning Models: A Survey for Practitioners [69.02688684221265]
  The use of sophisticated statistical models that influence decisions in domains of high societal relevance is on the rise. Many governments, institutions, and companies are reluctant to their adoption as their output is often difficult to explain in human-interpretable ways. Recently, the academic literature has proposed a substantial amount of methods for providing interpretable explanations to machine learning models.
  arXiv  Detail & Related papers  (2021-04-09T01:46:34Z)
• Bridging Machine Learning and Mechanism Design towards Algorithmic Fairness [6.6358581196331095]
  We argue that building fair decision-making systems requires overcoming limitations inherent to each field. We begin to lay the ground work towards this goal by comparing the perspective each discipline takes on fair decision-making.
  arXiv  Detail & Related papers  (2020-10-12T03:42:20Z)
• A Framework for Fairer Machine Learning in Organizations [0.0]
  Risk of unfairness abound when human decision processes in outcomes of socio-economic importance are automated. We reveal sources of unfair machine learning, review fairness criteria, and provide a framework which, if implemented, would enable an organization to avoid implementing an unfair machine learning model.
  arXiv  Detail & Related papers  (2020-09-10T04:07:10Z)
• Self-organizing Democratized Learning: Towards Large-scale Distributed Learning Systems [71.14339738190202]
  democratized learning (Dem-AI) lays out a holistic philosophy with underlying principles for building large-scale distributed and democratized machine learning systems. Inspired by Dem-AI philosophy, a novel distributed learning approach is proposed in this paper. The proposed algorithms demonstrate better results in the generalization performance of learning models in agents compared to the conventional FL algorithms.
  arXiv  Detail & Related papers  (2020-07-07T08:34:48Z)
• Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions [80.49176924360499]
  We establish a framework for directing a society of simple, specialized, self-interested agents to solve sequential decision problems. We derive a class of decentralized reinforcement learning algorithms. We demonstrate the potential advantages of a society's inherent modular structure for more efficient transfer learning.
  arXiv  Detail & Related papers  (2020-07-05T16:41:09Z)
• Distributed and Democratized Learning: Philosophy and Research Challenges [80.39805582015133]
  We propose a novel design philosophy called democratized learning (Dem-AI) Inspired by the societal groups of humans, the specialized groups of learning agents in the proposed Dem-AI system are self-organized in a hierarchical structure to collectively perform learning tasks more efficiently. We present a reference design as a guideline to realize future Dem-AI systems, inspired by various interdisciplinary fields.
  arXiv  Detail & Related papers  (2020-03-18T08:45:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.