Generalized strategic classification and the case of aligned incentives

S Levanon, N Rosenfeld - International Conference on …, 2022 - proceedings.mlr.press
Strategic classification studies learning in settings where self-interested users can
strategically modify their features to obtain favorable predictive outcomes. A key working …

Strategic instrumental variable regression: Recovering causal relationships from strategic responses

K Harris, DDT Ngo, L Stapleton… - … on Machine Learning, 2022 - proceedings.mlr.press
Abstract In settings where Machine Learning (ML) algorithms automate or inform
consequential decisions about people, individual decision subjects are often incentivized to …

Strategic apple tasting

K Harris, C Podimata, SZ Wu - Advances in Neural …, 2023 - proceedings.neurips.cc
Algorithmic decision-making in high-stakes domains often involves assigning decisions to
agents with incentives to strategically modify their input to the algorithm. In addition to …

On classification of strategic agents who can both game and improve

S Ahmadi, H Beyhaghi, A Blum, K Naggita - arXiv preprint arXiv …, 2022 - arxiv.org
In this work, we consider classification of agents who can both game and improve. For
example, people wishing to get a loan may be able to take some actions that increase their …

Strategic Evaluation

B Laufer, J Kleinberg, K Levy… - Proceedings of the 3rd …, 2023 - dl.acm.org
A broad current application of algorithms is in formal and quantitative measures of murky
concepts–like merit–to make decisions. When people strategically respond to these sorts of …

Strategic decision-making in the presence of information asymmetry: Provably efficient rl with algorithmic instruments

M Yu, Z Yang, J Fan - arXiv preprint arXiv:2208.11040, 2022 - arxiv.org
We study offline reinforcement learning under a novel model called strategic MDP, which
characterizes the strategic interactions between a principal and a sequence of myopic …

Performative recommendation: diversifying content via strategic incentives

I Eilat, N Rosenfeld - International Conference on Machine …, 2023 - proceedings.mlr.press
The primary goal in recommendation is to suggest relevant content to users, but optimizing
for accuracy often results in recommendations that lack diversity. To remedy this …

Sequential strategic screening

L Cohen, S Sharifi-Malvajerdi… - International …, 2023 - proceedings.mlr.press
We initiate the study of strategic behavior in screening processes with multiple classifiers.
We focus on two contrasting settings: a" conjunctive” setting in which an individual must …

Online bilevel optimization: Regret analysis of online alternating gradient methods

DA Tarzanagh, P Nazari, B Hou… - International …, 2024 - proceedings.mlr.press
This paper introduces\textit {online bilevel optimization} in which a sequence of time-varying
bilevel problems is revealed one after the other. We extend the known regret bounds for …

Strategic ML: How to Learn With Data That'Behaves'

N Rosenfeld - Proceedings of the 17th ACM International Conference …, 2024 - dl.acm.org
The success of machine learning across a wide array of tasks and applications has made it
appealing to use it also in the social domain. Indeed, learned models now form the …