Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
×
Jun 23, 2015 · In this paper, we formalize the problem, and pursue algorithms for learning classifiers that are robust to gaming.
People also ask
In this paper, we formalize the problem, and pursue algorithms for learning classifiers that are robust to gaming.
The goal of the strategic classification literature is to show when and how the firm can learn a robust classifier, which is guaranteed to perform well even.
In this work, we argue that the order of play in strategic classification is fundamentally tied to the relative update frequencies at which the decision-maker ...
Oct 3, 2024 · In strategic classification, agents manipulate their features, at a cost, to receive a positive classification outcome from the learner's ...
Strategic classification regards the problem of learning in settings where users can strategically modify their features to improve outcomes. This setting ...
We study an online linear classification problem in which the data is generated by strategic agents who manipulate their features in an effort to change the ...
Apr 24, 2023 · We propose a novel batch-learning setting in which we use unlabeled data from previous rounds to estimate the manipulation structure.
This paper formalizes the problem, and pursue algorithms for learning classifiers that are robust to gaming, and obtains computationally efficient learning ...
Strategic classification studies learning in a setting where users can 'game' the system by modifying their features, at a cost, to obtain favorable predictions ...