Learning Social Welfare Functions
Abstract: Is it possible to understand or imitate a policy maker's rationale by looking at past decisions they made? We formalize this question as the problem of learning social welfare functions belonging to the well-studied family of power mean functions. We focus on two learning tasks; in the first, the input is vectors of utilities of an action (decision or policy) for individuals in a group and their associated social welfare as judged by a policy maker, whereas in the second, the input is pairwise comparisons between the welfares associated with a given pair of utility vectors. We show that power mean functions are learnable with polynomial sample complexity in both cases, even if the comparisons are social welfare information is noisy. Finally, we design practical algorithms for these tasks and evaluate their performance.
- On the falsifiability and learnability of decision theories. Theoretical Economics, 15(4):1279–1305, 2020.
- Balanced Gray codes. the Electronic Journal of Combinatorics, 3(1):R25, 1996.
- Convex Optimization. Cambridge University Press, 2004.
- Rank analysis of incomplete block designs: I. the method of paired comparisons. Biometrika, 39:324, 1952.
- Condat, L. Fast projection onto the simplex and the l 1 ball. Mathematical Programming, 158(1):575–585, 2016.
- Cousins, C. An axiomatic theory of provably-fair welfare-centric machine learning. Advances in Neural Information Processing Systems, 34:16610–16621, 2021.
- Cousins, C. Revisiting fair PAC learning and the axioms of cardinal welfare. In International Conference on Artificial Intelligence and Statistics, pp. 6422–6442, 2023.
- Markets beyond Nash welfare for Leontief utilities. In 15th International Conference on Web and Internet Economics, 2019.
- Jameson, G. J. Counting zeros of generalised polynomials: Descartes’ rule of signs and Laguerre’s extensions. The Mathematical Gazette, 90(518):223–234, 2006.
- Kalai, G. Statistical learnability and rationality of choice. Technical report, Institute of Mathematics and Center for Rationality, The Hebrew University of Jerusalem, 2001.
- WeBuildAI: Participatory framework for algorithmic governance. Proceedings of the ACM on human-computer interaction, 3(CSCW):1–35, 2019.
- Fair resource allocation in federated learning. In 8th International Conference on Learning Representations, 2020.
- Luce, R. Individual Choice Behavior: A Theoretical Analysis. Dover, 2005.
- Learning to aggregate: Tackling the aggregation/disaggregation problem for OWA. In Proceedings of The Eleventh Asian Conference on Machine Learning, volume 101 of Proceedings of Machine Learning Research, pp. 1110–1125, 2019.
- Learning with noisy labels. Advances in Neural Information Processing Systems, 26, 2013.
- Learning aggregation functions. In Proceedings of the 30th International Joint Conference on Artificial Intelligence, pp. 2892–2898, 2021.
- The learnability of voting rules. Artificial Intelligence, 173(12):1133–1149, 2009.
- New proofs of weighted power mean inequalities and monotonicity for generalized weighted mean values. Mathematical Inequalities and Applications, 3:377–, 09 2000.
- Roberts, K. W. S. Interpersonal comparability and social choice theory. The Review of Economic Studies, 47(2):421–439, 1980.
- Tambe, M. (ed.). Security and Game Theory: Algorithms, Deployed Systems, Lessons Learned. Cambridge University Press, 2012.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.