Corpus ID: 235364020

Stateful Strategic Regression

@article{Harris2021StatefulSR,
  title={Stateful Strategic Regression},
  author={Keegan Harris and Hoda Heidari and Zhiwei Steven Wu},
  journal={ArXiv},
  year={2021},
  volume={abs/2106.03827}
}
Automated decision-making tools increasingly assess individuals to determine if they qualify for high-stakes opportunities. A recent line of research investigates how strategic agents may respond to such scoring tools to receive favorable assessments. While prior work has focused on the short-term strategic interactions between a decision-making institution (modeled as a principal) and individual decision-subjects (modeled as agents), we investigate interactions spanning multiple time-steps. In… Expand

Figures from this paper

References

SHOWING 1-10 OF 39 REFERENCES
The Disparate Effects of Strategic Manipulation
TLDR
This paper adapts models of strategic manipulation to capture dynamics that may arise in a setting of social inequality wherein candidate groups face different costs to manipulation, and finds that whenever one group's costs are higher than the other's, the learner's equilibrium strategy exhibits an inequality-reinforcing phenomenon. Expand
Strategic Classification is Causal Modeling in Disguise
TLDR
This work develops a causal framework for strategic adaptation and proves any procedure for designing classifiers that incentivize improvement must inevitably solve a non-trivial causal inference problem. Expand
On the Long-term Impact of Algorithmic Decision Policies: Effort Unfairness and Feature Segregation through Social Learning
TLDR
An effort-based measure of fairness is proposed and a data-driven framework for characterizing the long-term impact of algorithmic policies on reshaping the underlying population is presented. Expand
Simple versus Optimal Contracts
TLDR
This paper considers the classic principal-agent model of contract theory, and proves that linear contracts are guaranteed to be worst-case optimal, ranging over all reward distributions consistent with the given moments. Expand
Strategic Classification from Revealed Preferences
TLDR
For a broad family of agent cost functions, this work gives a computationally efficient learning algorithm that is able to obtain diminishing "Stackelberg regret" --- a form of policy regret that guarantees that the learner is realizing loss nearly as small as that of the best classifier in hindsight. Expand
How Do Classifiers Induce Agents to Invest Effort Strategically?
TLDR
A model for how strategic agents can invest effort in order to change the outcomes they receive is developed, and a tight characterization of when such agents can be incentivized to invest specified forms of effort into improving their outcomes is given. Expand
From Fair Decision Making To Social Equality
TLDR
A simple yet revealing model that encompasses a selection process where an institution chooses from multiple groups according to their qualifications so as to maximize an institutional utility and dynamics that govern the evolution of the groups' qualifications according to the imposed policies, and focuses on demographic parity as the formalism of affirmative action. Expand
Incentive compatible regression learning
TLDR
It is established that, in the general setting, the VCG mechanism goes a long way in guaranteeing truthfulness and economic efficiency. Expand
Watch and learn: optimizing from revealed preferences feedback
TLDR
This work gives algorithms for efficiently solving a broad class of Stackelberg games in which the follower's utility function is unknown, using only "revealed preference" access to it, which includes the profit maximization problem, as well as the optimal tolling problem in nonatomic congestion games, when the latency functions are unknown. Expand
The Social Cost of Strategic Classification
TLDR
It is proved that any increase in institutional utility necessarily leads to a corresponding increase in social burden, and highlighted that strategy-robustness must be weighed against considerations of social welfare and fairness. Expand
...
1
2
3
4
...