Incentive-Compatible Classification

Authors: Yakov Babichenko, Oren Dean, Moshe Tennenholtz7055-7062

AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We give upper bounds (impossibilities) and lower bounds (mechanisms) on the worst-case coincidence between the classification of an IC mechanism and the ideal α-classification. We prove bounds which depend on α and on the maximal number of reviews given by a single agent, Δ. Our results show that it is harder to find a good mechanism when α is smaller and Δ is larger. In particular, if Δ is unbounded, then the best mechanism is trivial (that is, it does not take into account the reviews). On the other hand, when Δ is sublinear in the number of agents, we give a simple, natural mechanism, with a coincidence ratio of α.
Researcher Affiliation Academia Yakov Babichenko, Oren Dean, Moshe Tennenholtz Technion Israel Institute of Technology Haifa, Israel
Pseudocode No The paper describes proposed mechanisms and their properties but does not include any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement about releasing source code or include links to a code repository.
Open Datasets No The paper is theoretical and does not describe experiments involving datasets for training.
Dataset Splits No The paper is theoretical and does not mention specific training, validation, or test dataset splits.
Hardware Specification No The paper does not describe any specific hardware used for running experiments, as it is a theoretical paper.
Software Dependencies No The paper does not list any specific software dependencies or versions for implementation, as it is a theoretical paper.
Experiment Setup No The paper is theoretical and does not provide details about an experimental setup, hyperparameters, or training configurations.