Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
126 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Non-linear Welfare-Aware Strategic Learning (2405.01810v2)

Published 3 May 2024 in cs.AI and cs.LG

Abstract: This paper studies algorithmic decision-making in the presence of strategic individual behaviors, where an ML model is used to make decisions about human agents and the latter can adapt their behavior strategically to improve their future data. Existing results on strategic learning have largely focused on the linear setting where agents with linear labeling functions best respond to a (noisy) linear decision policy. Instead, this work focuses on general non-linear settings where agents respond to the decision policy with only "local information" of the policy. Moreover, we simultaneously consider the objectives of maximizing decision-maker welfare (model prediction accuracy), social welfare (agent improvement caused by strategic behaviors), and agent welfare (the extent that ML underestimates the agents). We first generalize the agent best response model in previous works to the non-linear setting, then reveal the compatibility of welfare objectives. We show the three welfare can attain the optimum simultaneously only under restrictive conditions which are challenging to achieve in non-linear settings. The theoretical results imply that existing works solely maximizing the welfare of a subset of parties inevitably diminish the welfare of the others. We thus claim the necessity of balancing the welfare of each party in non-linear settings and propose an irreducible optimization algorithm suitable for general strategic learning. Experiments on synthetic and real data validate the proposed algorithm.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (45)
  1. The strategic perceptron. In Proceedings of the 22nd ACM Conference on Economics and Computation, pages 6–25, 2021.
  2. On classification of strategic agents who can both game and improve. arXiv preprint arXiv:2203.00124, 2022a.
  3. Setting fair incentives to maximize improvement. arXiv preprint arXiv:2203.00134, 2022b.
  4. Multiagent evaluation mechanisms. Proceedings of the AAAI Conference on Artificial Intelligence, 34:1774–1781, 2020.
  5. Transparency, detection and imitation in strategic classification. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI-22, pages 67–73, 2022.
  6. Gaming helps! learning from strategic interactions in natural dynamics. In International Conference on Artificial Intelligence and Statistics, pages 1234–1242, 2021.
  7. Information discrepancy in strategic learning. In International Conference on Machine Learning, pages 1691–1715, 2022.
  8. Best response regression. In Advances in Neural Information Processing Systems, 2017.
  9. The role of randomness and noise in strategic classification. CoRR, abs/2005.08377, 2020.
  10. Strategic recourse in linear classification. CoRR, abs/2011.00355, 2020a.
  11. Learning strategy-aware linear classifiers. Advances in Neural Information Processing Systems, 33:15265–15276, 2020b.
  12. Emergent segmentation from participation dynamics and multi-learner retraining, 2023.
  13. Retiring adult: New datasets for fair machine learning. Advances in neural information processing systems, 34:6478–6490, 2021.
  14. Strategic classification from revealed preferences. In Proceedings of the 2018 ACM Conference on Economics and Computation, page 55–70, 2018.
  15. UCI machine learning repository, 2017. URL https://archive.ics.uci.edu/ml/datasets/credit+approval.
  16. Strategic classification with graph neural networks, 2022.
  17. Runaway feedback loops in predictive policing. In Conference on fairness, accountability and transparency, pages 160–171. PMLR, 2018.
  18. Incentivizing truthfulness through audits in strategic classification. In Proceedings of the AAAI Conference on Artificial Intelligence, number 6, pages 5347–5354, 2021.
  19. Massimo Florio. Applied welfare economics: Cost-benefit analysis of projects and policies. Routledge, 2014.
  20. Equal improvability: A new fairness notion considering the long-term impact. In The Eleventh International Conference on Learning Representations, 2022.
  21. Performative prediction: Past and future. arXiv preprint arXiv:2310.16608, 2023.
  22. Strategic classification. In Proceedings of the 2016 ACM Conference on Innovations in Theoretical Computer Science, page 111–122, 2016.
  23. Stateful strategic regression. Advances in Neural Information Processing Systems, pages 28728–28741, 2021.
  24. On the long-term impact of algorithmic decision policies: Effort unfairness and feature segregation through social learning. In 36th International Conference on Machine Learning, pages 2692–2701, 2019.
  25. Causal strategic classification: A tale of two shifts, 2023.
  26. How to learn when data reacts to your model: Performative gradient descent. In Proceedings of the 38th International Conference on Machine Learning, pages 4641–4650, 2021.
  27. Alternative microfoundations for strategic classification. In Proceedings of the 38th International Conference on Machine Learning, pages 4687–4697, 2021.
  28. Identifying and correcting label bias in machine learning. In International Conference on Artificial Intelligence and Statistics, pages 702–712. PMLR, 2020.
  29. Incentive mechanisms for strategic classification and regression problems. In Proceedings of the 23rd ACM Conference on Economics and Computation, page 760–790, 2022.
  30. How do classifiers induce agents to invest effort strategically? page 1–23, 2020.
  31. Strategic classification made practical. In International Conference on Machine Learning, pages 6243–6253. PMLR, 2021.
  32. Generalized strategic classification and the case of aligned incentives. In International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA, pages 12593–12618, 2022.
  33. Delayed impact of fair machine learning. In Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19, pages 6196–6200, 2019.
  34. The disparate equilibria of algorithmic decision making when individuals invest rationally. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, pages 381–391, 2020.
  35. Strategic classification is causal modeling in disguise. In Proceedings of the 37th International Conference on Machine Learning, 2020.
  36. The social cost of strategic classification. In Proceedings of the Conference on Fairness, Accountability, and Transparency, pages 230–239, 2019.
  37. Performative prediction. In Proceedings of the 37th International Conference on Machine Learning, pages 7599–7609, 2020.
  38. Unintended selection: Persistent qualification rate disparities and interventions. Advances in Neural Information Processing Systems, pages 26053–26065, 2021.
  39. Balancing competing objectives with noisy data: Score-based classifiers for welfare-aware machine learning. In International Conference on Machine Learning, pages 8158–8168. PMLR, 2020.
  40. From predictions to decisions: Using lookahead regularization. In Advances in Neural Information Processing Systems, pages 4115–4126, 2020.
  41. Causal strategic linear regression. In Proceedings of the 37th International Conference on Machine Learning, ICML’20, 2020.
  42. Pac-learning for strategic classification. In Proceedings of the 38th International Conference on Machine Learning, pages 9978–9988, 2021.
  43. Linear models are robust optimal under strategic behavior. In Proceedings of The 24th International Conference on Artificial Intelligence and Statistics, volume 130 of Proceedings of Machine Learning Research, pages 2584–2592, 13–15 Apr 2021.
  44. How do fair decisions fare in long-term qualification? In Advances in Neural Information Processing Systems, pages 18457–18469, 2020.
  45. Fairness interventions as (Dis)Incentives for strategic manipulation. In Proceedings of the 39th International Conference on Machine Learning, pages 26239–26264, 2022.
Citations (4)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets