Strategic Classification
The DOI matches its Crossref record; 2 of the 2 references it cites were found in a registry or an index.
Abstract
Machine learning relies on the assumption that unseen test instances of a classification problem follow the same distribution as observed training data. However, this principle can break down when machine learning is used to make important decisions about the welfare (employment, education, health) of strategic individuals. Knowing information about the classifier, such individuals may manipulate their attributes in order to obtain a better classification outcome. As a result of this behavior -- often referred to as gaming -- the performance of the classifier may deteriorate sharply. Indeed, gaming is a well-known obstacle for using machine learning methods in practice; in financial policy-making, the problem is widely known as Goodhart's law. In this paper, we formalize the problem, and pursue algorithms for learning classifiers that are robust to gaming.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Valiant, L. G. (1984) · Communications of the ACM · doi:10.1145/1968.1972 · Cited by 3,279
Stackelberg games for adversarial prediction problems
Brückner, M., & Scheffer, T. (2011) · Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining · doi:10.1145/2020408.2020495 · Cited by 229
Research works printed but not linked: 12
- Stéphane Boucheron , Olivier Bousquet , and Gábor Lugosi . Theory of classification: A survey of some recent advances. ESAIM: probability and statistics, 9:323--375 , 2005 . Stéphane Boucheron, Olivier Bousquet, and Gábor Lugosi. Theory of classification: A survey of some recent advances. ESAIM: probability and statistics, 9:323--375, 2005.
- 10.5555/2503308.2503326 · doi:10.5555/2503308.2503326
- Michael Brückner and Tobias Scheffer . Nash equilibria of static prediction games . In Proc. 23rd NIPS 2009 , pages 171 -- 179 , 2009 . Michael Brückner and Tobias Scheffer. Nash equilibria of static prediction games. In Proc. 23rd NIPS 2009, pages 171--179, 2009.
- 10.1016/j.ins.2014.03.108 · DOI
- Danielle Keats Citron and Frank Pasquale . The scored society: Due process for automated predictions. 89 Washington Law Review, 1 , 2014 . Danielle Keats Citron and Frank Pasquale. The scored society: Due process for automated predictions. 89 Washington Law Review, 1, 2014.
- 10.1145/1014052.1014066 · DOI · Paper page
- 10.1016/j.rssm.2010.01.002 · DOI · Paper page
- Michael Großhans , Christoph Sawade , Michael Brückner , and Tobias Scheffer . Bayesian games for adversarial regression problems . In Proc. 30th ICML , pages 55 -- 63 , 2013 . Michael Großhans, Christoph Sawade, Michael Brückner, and Tobias Scheffer. Bayesian games for adversarial regression problems. In Proc. 30th ICML, pages 55--63, 2013.
- Moritz Hardt , Nimrod Megiddo , Christos H. Papadimitriou , and Mary Wootters . Strategic classification. CoRR, abs/1506.06980 , 2015 . Moritz Hardt, Nimrod Megiddo, Christos H. Papadimitriou, and Mary Wootters. Strategic classification. CoRR, abs/1506.06980, 2015. · arXiv
- Dmytro Korzhyk , Vincent Conitzer , and Ronald Parr . Complexity of computing optimal Stackelberg strategies in security resource allocation games . In Proc. AAAI , 2010 . Dmytro Korzhyk, Vincent Conitzer, and Ronald Parr. Complexity of computing optimal Stackelberg strategies in security resource allocation games. In Proc. AAAI, 2010.
- Dmytro Korzhyk , Zhengyu Yin , Christopher Kiekintveld , Vincent Conitzer , and Milind Tambe . Stackelberg vs. Nash in security games: An extended investigation of interchangeability, equivalence, and uniqueness. J. Artif. Intell. Res.(JAIR), 41:297--327 , 2011 . Dmytro Korzhyk, Zhengyu Yin, Christopher Kiekintveld, Vincent Conitzer, and Milind Tambe. Stackelberg vs. Nash in security games: An extended investigation of interchangeability, equivalence, and uniqueness. J. Artif. Intell. Res.(JAIR), 41:297--327, 2011.
- Michel Ledoux and Michel Talagrand . Probability in Banach Spaces: isoperimetry and processes , volume 23 . Springer , 1991 . Michel Ledoux and Michel Talagrand. Probability in Banach Spaces: isoperimetry and processes, volume 23. Springer, 1991. · DOI · Paper page
Cited by
Lepri, B., Oliver, N., Letouzé, E., Pentland, A., & Vinck, P. (2018) · Philosophy & Technology · doi:10.1007/s13347-017-0279-x · Cited by 709
“[28] have proposed adversarial methods for de-”
Actionable Recourse in Linear Classification
Ustun, B., Spangher, A., & Liu, Y. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287566 · Cited by 501
Inherent Tradeoffs in the Fair Determination of Risk Scores
(2023) · The Societal Impacts of Algorithmic Decision-Making · doi:10.1145/3603195.3603197 · Cited by 310
A Survey of Algorithmic Recourse: Contrastive Explanations and Consequential Recommendations
Karimi, A.-H., Barthe, G., Schölkopf, B., & Valera, I. (2023) · ACM Computing Surveys · doi:10.1145/3527848 · Cited by 301
de Laat, P. B. (2018) · Philosophy & Technology · doi:10.1007/s13347-017-0293-z · Cited by 251
“First results (concerning spam filtering) indicate that such dynamic classifiers perform somewhat better against gaming adversaries than static ones (Brückner et al. 2012; Hardt et al. 2016).”
BackgroundHow to talk when a machine is listening: Corporate disclosure in the age of AI
Cao, S., Jiang, W., Yang, B., & Zhang, A. L. (2023) · The Review of Financial Studies · doi:10.1093/rfs/hhad021 · Cited by 222
The philosophical basis of algorithmic recourse
Venkatasubramanian, S., & Alfano, M. (2020) · Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency · doi:10.1145/3351095.3372876 · Cited by 114
“The second aspect draws a contrast with other literature that considers the problem of strategic manipulation of features to achieve a desired goal[14, 16, 24].”
BackgroundThis Thing Called Fairness: Disciplinary Confusion Realizing a Value in Technology
Mulligan, D. K., Kroll, J. A., Kohli, N., & Wong, R. Y. (2019) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3359221 · Cited by 111
Beyond generalization: a theory of robustness in machine learning
Freiesleben, T., & Grote, T. (2023) · Synthese · doi:10.1007/s11229-023-04334-9 · Cited by 106
“, by making small financial transactions to boost one’s credit score (Hardt et al., 2016).”
BackgroundTirole, J. (2021) · American Economic Review · doi:10.1257/aer.20201214 · Cited by 75
Mechanism design for social good
Abebe, R., & Goldner, K. (2018) · AI Matters · doi:10.1145/3284751.3284761 · Cited by 45
General intelligence requires rethinking exploration
Jiang, M., Rocktäschel, T., & Grefenstette, E. (2022) · arXiv · doi:10.48550/arxiv.2211.07819 · Cited by 17
GOODHART'S LAW AND MACHINE LEARNING: A STRUCTURAL PERSPECTIVE
Hennessy, C. A., & Goodhart, C. A. E. (2023) · International Economic Review · doi:10.1111/iere.12633 · Cited by 8
Formal contracts mitigate social dilemmas in multi-agent reinforcement learning
Haupt, A., Christoffersen, P., Damani, M., & Hadfield-Menell, D. (2024) · Autonomous Agents and Multi-Agent Systems · doi:10.1007/s10458-024-09682-5 · Cited by 5
“Stackelberg learning has received a lot of attention in strategic Machine Learning [12, 25, 44] and has been used to learn large scale mechanisms such as auctions [3, 6].”
A Classification of Feedback Loops and Their Relation to Biases in Automated Decision-Making Systems
Pagan, N., Baumann, J., Elokda, E., De Pasquale, G., Bolognani, S., & Hannák, A. (2023) · arXiv · doi:10.48550/arxiv.2305.06055 · Cited by 4
Feedback Loops With Language Models Drive In-Context Reward Hacking
Pan, A., Jones, E., Jagadeesan, M., & Steinhardt, J. (2024) · arXiv · doi:10.48550/arxiv.2402.06627 · Cited by 3
“…repeated rounds of deployment with a classifier may worsen performance on minority groups (Hashimoto et al., 2018), incentivize users to strategically change their features (Brückner & Scheffer, 2009; Hardt et al., 2016), or induce other forms of distributions shifts (Perdomo et al., 2020).”
BackgroundAlgorithmic monoculture and social welfare
(2023) · The Societal Impacts of Algorithmic Decision-Making · doi:10.1145/3603195.3603202
Metadata
- Authors
- Hardt, M., Megiddo, N., Papadimitriou, C., & Wootters, M.
- Venue
- Proceedings of the 2016 ACM Conference on Innovations in Theoretical Computer Science
- Publisher
- ACM
- Published
- 2016-01-14
- Pages
- 111-122
- OpenAlex
- W2913525780
- Cited by
- 223
- References
- 2
- FWCI
- 7.81
- Type
- conference paper
- Language
- en
- Open access
- closed
- Funders
- Templeton Foundation (3966)
- National Science Foundation (DMS-1400558, CCF1408635)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.