Strategyproof Classification under Constant Hypotheses: A Tale of Two Functions
A PHP Error was encountered
Message: Undefined index: id
Line Number: 218
We consider the following setting: a decision maker must make a decision based on reported data points with binary labels. Subsets of data points are controlled by different self- ish agents, which might misreport the labels in order to sway the decision in their favor. We design mechanisms (both de- terministic and randomized) that reach an approximately op- timal decision and are strategyproof, i.e., agents are best off when they tell the truth. We then recast our results into a classical machine learning classification framework, where the decision maker must make a decision (choose between the constant positive hypothesis and the constant negative hypothesis) based only on a sampled subset of the agents' points.