Automated Mechanism Design without Money via Machine Learning
Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. Pages 433-438.
Abstract
We use statistical machine learning to develop methods for automatically designing mechanisms in domains without money. Our goal is to find a mechanism that best approximates a given target function subject to a design constraint such as strategy-proofness or stability. The proposed approach involves identifying a rich parametrized class of mechanisms that resemble discriminant-based multiclass classifiers, and relaxing the resulting search problem into an SVM-style surrogate optimization problem. We use this methodology to design strategy-proof mechanisms for social choice problems with single-peaked preferences, and stable mechanisms for two-sided matching problems. To the best of our knowledge, ours is the first automated approach for designing stable matching rules. Experiments on synthetic and real-world data confirm the usefulness of our methods.
@inproceedings{ijcai2016p68,
title = {Automated Mechanism Design without Money via Machine Learning},
author = {Narasimhan, Harikrishna and Agarwal, Shivani and Parkes, David C.},
booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI-16}},
publisher = {AAAI Press / International Joint Conferences on Artificial Intelligence},
editor = {Subbarao Kambhampati},
pages = {433--438},
year = {2016},
month = {7},
url = {https://ijcai.org/proceedings/2016/68},
}
TY - CPAPER TI - Automated Mechanism Design without Money via Machine Learning AU - Narasimhan, Harikrishna AU - Agarwal, Shivani AU - Parkes, David C. T2 - Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16 PB - AAAI Press / International Joint Conferences on Artificial Intelligence PY - 2016 SP - 433 EP - 438 UR - https://ijcai.org/proceedings/2016/68 ER -Copied
Machine-readable versions of this paper, for tools and AI agents: