Papers
Topics
Authors
Recent
Search
2000 character limit reached

Learning In Reverse Causal Strategic Environments With Ramifications on Two Sided Markets

Published 20 Apr 2024 in stat.ML, cs.GT, and cs.LG | (2404.13240v1)

Abstract: Motivated by equilibrium models of labor markets, we develop a formulation of causal strategic classification in which strategic agents can directly manipulate their outcomes. As an application, we compare employers that anticipate the strategic response of a labor force with employers that do not. We show through a combination of theory and experiment that employers with performatively optimal hiring policies improve employer reward, labor force skill level, and in some cases labor force equity. On the other hand, we demonstrate that performative employers harm labor force utility and fail to prevent discrimination in other cases.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (55)
  1. Multiagent evaluation mechanisms. In AAAI Conference on Artificial Intelligence, 2020.
  2. Employer learning and statistical discrimination. The Quarterly Journal of Economics, 116(1):313–350, 2001.
  3. Does affirmative action lead to mismatch? a new test and evidence. Quantitative Economics, 2(3):303–333, 2011.
  4. Kenneth Arrow. The theory of discrimination. Labor Economics vol 4, 1971.
  5. Transparency, detection and imitation in strategic classification. In International Joint Conferences on Artificial Intelligence, 2022.
  6. Information discrepancy in strategic learning. In International Conference on Machine Learning, 2022.
  7. Performative Prediction in a Stateful World. In International Conference on Artificial Intelligence and Statistics, 2022.
  8. Static prediction games for adversarial learning problems. Journal of Machine Learning Research, 13(85):2617–2654, 2012. URL http://jmlr.org/papers/v13/brueckner12a.html.
  9. Learning strategy-aware linear classifiers. In Conference On Neural Information Processing Systems, 2020.
  10. Will Affirmative-Action Policies Eliminate Negative Stereotypes? The American Economic Review, 83(5):1220–1240, 1993. ISSN 0002-8282.
  11. Complementary bias: A model of two-sided statistical discrimination. Working Paper 23811, National Bureau of Economic Research, 2017.
  12. Strategic classification from revealed preferences. In Proceedings of the 2018 ACM Conference On Economics and Computation, 2018.
  13. Stochastic optimization with decision-dependent distributions. https://arxiv.org/abs/2011.11173, 2020.
  14. Chapter 5 - theories of statistical discrimination and affirmative action: A survey. volume 1 of Handbook of Social Economics, pages 133–200. North-Holland, 2011a. doi: https://doi.org/10.1016/B978-0-444-53187-2.00005-X. URL https://www.sciencedirect.com/science/article/pii/B978044453187200005X.
  15. Chapter 5 - Theories of Statistical Discrimination and Affirmative Action: A Survey. In Jess Benhabib, Alberto Bisin, and Matthew O. Jackson, editors, Handbook of Social Economics, volume 1, pages 133–200. North-Holland, January 2011b. doi: 10.1016/B978-0-444-53187-2.00005-X.
  16. Affirmative action in winner-take-all markets. The Journal of Economic Inequality, 2005.
  17. Valuing diversity. Journal of Political Economy, 2013.
  18. An economic analysis of color-blind affirmative action. The Journal of Law, Economics, and Organization., 2008.
  19. Strategic classification in the dark. In International Conference on Machine Learning, 2021.
  20. On-demand sampling: Learning optimally from multiple distributions. https://arxiv.org/abs/2210.12529, 2023.
  21. Strategic classification, 2015.
  22. Strategic instrumental variable regression: Recovering causal relationships from strategic responses. In International Conference on Machine Learning. PMLR, 2022.
  23. A Tale of Two Shifts: Causal Strategic Classification. https://arxiv.org/pdf/2302.06280.pdf, 2023.
  24. Modeling content creator incentives on algorithm-curated platforms. In The Eleventh International Conference on Learning Representations, February 2023.
  25. 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. PMLR, July 2021.
  26. How to Learn when Data Gradually Reacts to Your Model. In Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, pages 3998–4035. PMLR, May 2022.
  27. Alternative Microfoundations for Strategic Classification. In International Conference on Machine Learning, 2021.
  28. Regret minimization with performative feedback. In International Conference on Machine Learning, 2022.
  29. Supply-side equilibria in reccommender systems. https://arxiv.org/pdf/2206.13489.pdf, 2023.
  30. Downstream effects of affirmative action. In Proceedings of the Conference on Fairness, Accountability, and Transparency, FAT* ’19, page 240–248, New York, NY, USA, 2019. Association for Computing Machinery. ISBN 9781450361255. doi: 10.1145/3287560.3287578. URL https://doi.org/10.1145/3287560.3287578.
  31. Algorithmic recourse: from counterfactual explanations to interventions. In ACM conference on fairness, accountability, and transparency, 2021.
  32. How do classifiers induce agents to invest strategically? ACM Transactions on Economics and Computation, 2020.
  33. Improvement-focused causal recourse (icr). In AAAI Conference On Artificial Intelligence, 2023.
  34. Strategic Classification Made Practical. In International Conference on Machine Learning, 2021.
  35. Generalized strategic classification and the case of aligned incentives. In International Conference on Machine Learning, 2022.
  36. The disparate equilibria of algorithmic decision making when individuals invest rationally. In ACM Conference on Fairness, Accountability, and Transparency in Machine Learning, 2020.
  37. Strategic ranking. In Proceedings of The 25th International Conference on Artificial Intelligence and Statistics, 2022.
  38. A linear adjustment based approach to posterior drift in transfer learning. arXiv:2111.10841 [stat], December 2021.
  39. Predictor-corrector algorithms for stochastic optimization under gradual distribution shift. In The Eleventh International Conference on Learning Representations, September 2022a.
  40. Understanding new tasks through the lens of training data via exponential tilting. In The Eleventh International Conference on Learning Representations, September 2022b.
  41. Stochastic optimization for performative prediction. In Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS’20, pages 4929–4939, Red Hook, NY, USA, December 2020. Curran Associates Inc. ISBN 978-1-71382-954-6.
  42. Anticipating performativity by predicting from predictions. In Conference on Neural Information Processing Systems, 2022.
  43. Strategic Classification is Causal Modeling in Disguise. arXiv:1910.10362 [cs, stat], February 2020.
  44. Outside the Echo Chamber: Optimizing the Performative Risk. In International Conference on Machine Learning, 2021.
  45. The social cost of strategic classification, 2018.
  46. Affirmative action in a competitive economy. Journal of Public Economics, 87(3-4):567–594, March 2003. ISSN 00472727. doi: 10.1016/S0047-2727(01)00121-9.
  47. A general equilibrium model of statistical discrimination. Journal of Economic Theory, 114(1):1–30, January 2004. ISSN 00220531. doi: 10.1016/S0022-0531(03)00165-0.
  48. Performative Prediction. In Proceedings of the 37th International Conference on Machine Learning, pages 7599–7609. PMLR, November 2020.
  49. Edmund Phelps. The statistical theory of racism and sexism. The American Economic Review, 1972.
  50. Causal strategic linear regression. In International Conference on Machine Learning, 2020.
  51. SciPy 1.0: Fundamental Algorithms for Scientific Computing in Python. Nature Methods, 17:261–272, 2020. doi: 10.1038/s41592-019-0686-2.
  52. Ronald J. Williams. Simple statistical following algorithms for connectionist reinforcement learning. Machine Learning, 1992.
  53. Online projected gradient descent for stochastic optimization with descision dependent distributions. IEEE Control Systems Letters, 2021.
  54. Strategic decision-making in the presence of information asymmetry: Provably efficient reinforcement learning with algorithmic instruments. https://arxiv.org/pdf/2208.11040.pdf, 2022.
  55. Who leads and who follows in strategic classification? In Advances in Neural Information Processing Systems, 2021.
Citations (4)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up

Tweets

Sign up for free to view the 3 tweets with 0 likes about this paper.

Sign Up for Free