Learning the Distribution Map in Reverse Causal Performative Prediction
Abstract: In numerous predictive scenarios, the predictive model affects the sampling distribution; for example, job applicants often meticulously craft their resumes to navigate through a screening systems. Such shifts in distribution are particularly prevalent in the realm of social computing, yet, the strategies to learn these shifts from data remain remarkably limited. Inspired by a microeconomic model that adeptly characterizes agents' behavior within labor markets, we introduce a novel approach to learn the distribution shift. Our method is predicated on a reverse causal model, wherein the predictive model instigates a distribution shift exclusively through a finite set of agents' actions. Within this framework, we employ a microfoundation model for the agents' actions and develop a statistically justified methodology to learn the distribution shift map, which we demonstrate to be effective in minimizing the performative prediction risk.
- Wasserstein generative adversarial networks. In International conference on machine learning, pages 214–223. PMLR, 2017.
- On matrix estimation under monotonicity constraints. Bernoulli, 24(2):1072–1100, May 2018. ISSN 1350-7265. doi: 10.3150/16-BEJ865.
- Learning strategy-aware linear classifiers. Advances in Neural Information Processing Systems, 33:15265–15276, 2020.
- Will Affirmative-Action Policies Eliminate Negative Stereotypes? The American Economic Review, 83(5):1220–1240, 1993. ISSN 0002-8282.
- Launch and iterate: Reducing prediction churn. In Proceedings of the 30th International Conference on Neural Information Processing Systems, NIPS’16, pages 3179–3187, Red Hook, NY, USA, December 2016. Curran Associates Inc. ISBN 978-1-5108-3881-9.
- Stochastic optimization under time drift: iterate averaging, step decay, and high probability guarantees. arXiv preprint arXiv:2108.07356, 2021.
- Strategic Classification from Revealed Preferences. In Proceedings of the 2018 ACM Conference on Economics and Computation, EC ’18, pages 55–70, New York, NY, USA, June 2018. Association for Computing Machinery. ISBN 978-1-4503-5829-3. doi: 10.1145/3219166.3219193.
- Generative adversarial nets. Advances in neural information processing systems, 27, 2014.
- Isotonic regression in general dimensions. The Annals of Statistics, 47(5):2440–2471, October 2019. ISSN 0090-5364, 2168-8966. doi: 10.1214/18-AOS1753.
- Strategic Classification. arXiv:1506.06980 [cs], November 2015.
- Strategic Classification. In Proceedings of the 2016 ACM Conference on Innovations in Theoretical Computer Science, ITCS ’16, pages 111–122, New York, NY, USA, January 2016. Association for Computing Machinery. ISBN 978-1-4503-4057-1. doi: 10.1145/2840728.2840730.
- Causal strategic classification: A tale of two shifts. In International Conference on Machine Learning, pages 13233–13253. PMLR, 2023.
- 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.
- Regret Minimization with Performative Feedback. In Proceedings of the 39th International Conference on Machine Learning, pages 9760–9785. PMLR, June 2022.
- Sequential covariate shift detection using classifier two-sample tests. In International Conference on Machine Learning, pages 9845–9880. PMLR, 2022.
- Strategic Classification Made Practical, June 2021.
- Generalized strategic classification and the case of aligned incentives. In International Conference on Machine Learning, pages 12593–12618. PMLR, 2022.
- Plug-in performative optimization. arXiv preprint arXiv:2305.18728, 2023.
- Detecting and Correcting for Label Shift with Black Box Predictors. arXiv:1802.03916 [cs, stat], July 2018.
- Understanding new tasks through the lens of training data via exponential tilting. In The Eleventh International Conference on Learning Representations, September 2022.
- Mary C Meyer. Inference using shape-restricted regression splines. 2008.
- Outside the Echo Chamber: Optimizing the Performative Risk. In Proceedings of the 38th International Conference on Machine Learning, pages 7710–7720. PMLR, July 2021.
- Monotone least squares and isotonic quantiles. 2020.
- Hans-Georg Müller. Optimal designs for nonparametric kernel regression. Statistics & Probability Letters, 2(5):285–290, 1984.
- Performative Prediction. arXiv:2002.06673 [cs, stat], June 2020.
- Order restricted statistical inference. (No Title), 1988.
- Causal strategic linear regression. In International Conference on Machine Learning, pages 8676–8686. PMLR, 2020.
- Learning in reverse causal strategic environments with ramifications on two sided markets. In The Twelfth International Conference on Learning Representations, 2024. URL https://openreview.net/forum?id=vEfmVS5ywF.
- Marilyn Strathern. ‘improving ratings’: audit in the british university system. European review, 5(3):305–321, 1997.
- Sequential design for nonparametric inference. Canadian Journal of Statistics, 40(2):362–377, 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.