{"type":"ScholarlyArticle","title":"Deep Learning for Multi-Facility Location Mechanism Design","authors":[{"name":"Noah Golowich","slug":"noah-golowich","given":"Noah","family":"Golowich","affiliation":"Harvard University , SEAS , 33 Oxford Street , Cambridge , MA , 02138"},{"name":"Harikrishna Narasimhan","slug":"harikrishna-narasimhan","given":"Harikrishna","family":"Narasimhan","affiliation":"Harvard University , SEAS , 33 Oxford Street , Cambridge , MA , 02138"},{"name":"David C. Parkes","slug":"david-c-parkes","given":"David C.","family":"Parkes","affiliation":"Harvard University , SEAS , 33 Oxford Street , Cambridge , MA , 02138"}],"abstract":"Moulin [1980] characterizes the single-facility, deterministic strategy-proof mechanisms for social choice with single-peaked preferences as the set of generalized median rules. In contrast, we have only a limited understanding of multi-facility strategy-proof mechanisms, and recent work has shown negative worst case results for social cost. Our goal is to design strategy-proof, multi-facility mechanisms that minimize expected social cost. We first give a PAC learnability result for the class of multi-facility generalized median rules, and utilize neural networks to learn mechanisms from this class. Even in the absence of characterization results, we develop a computational procedure for learning almost strategy-proof mechanisms that are as good as or better than benchmarks from the literature, such as the best percentile and dictatorial rules.","doi":"10.24963/ijcai.2018/36","url":"https://ijcai.org/proceedings/2018/36","pdf":"https://ijcai.org/proceedings/2018/0036.pdf","markdown":"https://ijcai.org/proceedings/2018/36.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/36","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Agent-based and Multi-agent Systems","track":"Main track","number":36,"pages":{"first":261,"last":267},"keywords":["Agent-based and Multi-agent Systems: Computational Social Choice","Agent-based and Multi-agent Systems: Algorithmic Game Theory","Machine Learning: Neural Networks"],"videos":[],"references":[{"position":1,"raw":"[Alon et al., 2010] Noga Alon, Michal Feldman, Ariel D. Procaccia, and Moshe Tennenholtz. Strategyproof approx- imation of the minimax on networks. Mathematics of Op- erations Research, 35(3):513-526, 2010.","title":"Strategyproof approximation of the minimax on networks","authors":"Noga Alon, Michal Feldman, Ariel D Procaccia, Moshe Tennenholtz","year":"2010","venue":"Mathematics of Operations Research","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Anthony and Bartlett, 2009] Martin Anthony and Peter L. Bartlett. Neural Network Learning: Theoretical Founda- tions. Cambridge University Press, 2009.","title":"Neural Network Learning: Theoretical Foundations","authors":"Martin Anthony, Peter L Bartlett","year":"2009","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Barberà et al., 1993] Salvador Barberà, F Gul, and E Stac- chetti. Generalized median voter schemes and committees. Journal of Economic Theory, 61:262-289, 1993.","title":"Salvador Barberà, F Gul, and E Stacchetti. Generalized median voter schemes and committees","authors":"Barberà","year":"1993","venue":"Journal of Economic Theory","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Black, 1948] Duncan Black. On the Rationale of Group Decision-making. Journal of Political Economy, 56(1):23-34, 1948.","title":"On the Rationale of Group Decision-making","authors":"Duncan Black","year":"1948","venue":"Journal of Political Economy","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Border and Jordan, 1983] Kim C. Border and J. S. Jordan. Straightforward Elections, Unanimity and Phantom Vot- ers. Review of Economic Studies, 50(1):153, 1983.","title":"Straightforward Elections, Unanimity and Phantom Voters","authors":"Kim C Border, J S Jordan","year":"1983","venue":"Review of Economic Studies","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cai and Daskalakis, 2017] Yang Cai and Constantinos Daskalakis. Learning multi-item auctions with (or with- out) samples. In Proceedings of the IEEE 58th Annual Symposium on Foundations of Computer Science, 2017.","title":"Learning multi-item auctions with (or without) samples","authors":"Yang Cai, Constantinos Daskalakis","year":"2017","venue":"Proceedings of the IEEE 58th Annual Symposium on Foundations of Computer Science","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Conitzer and Sandholm, 2002] Vincent Conitzer and Tuo- mas Sandholm. Complexity of mechanism design. In Pro- ceedings of the Eighteenth conference on Uncertainty in artificial intelligence, 2002.","title":"Complexity of mechanism design","authors":"Sandholm ; Conitzer, Tuomas Conitzer, Sandholm","year":"2002","venue":"Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Dütting et al., 2015] Paul Dütting, Felix Fischer, Pichayut Jirapinyo, John K. Lai, Benjamin Lubin, and David C. Parkes. Payment Rules through Discriminant-Based Clas- sifiers. ACM Transactions on Economics and Computa- tion, 3(1):1-41, 2015.","title":"Payment Rules through Discriminant-Based Classifiers","authors":"Paul Dütting, Felix Fischer, Pichayut Jirapinyo, John K Lai, Benjamin Lubin, David C Parkes","year":"2015","venue":"ACM Transactions on Economics and Computation","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Dütting et al., 2017] Paul Dütting, Zhe Feng, Harikrishna Narasimhan, and David C. Parkes. Optimal Auctions through Deep Learning. ArXiv:1706.03459 [cs], 2017.","title":"Optimal Auctions through Deep Learning","authors":"Paul Dütting, Zhe Feng, Harikrishna Narasimhan, David C Parkes","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Ehlers and Gordon, 2011] Lars Ehlers and Sidartha Gor- don. Strategy-proof provision of two public goods: the LexMax extension. Technical report, Mimeo Université de Montréal, 2011.","title":"Lars Ehlers and Sidartha Gordon. Strategy-proof provision of two public goods: the LexMax extension","authors":"Gordon Ehlers","year":"2011","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Feng et al., 2018] Zhe Feng, Harikrishna Narasimhan, and David C. Parkes. Deep Learning for Revenue-Optimal Auctions with Budgets. In Proceedings of the 17th In- ternational Conference on Autonomous Agents and Multi- agent Systems, 2018. To appear.","title":"Deep Learning for Revenue-Optimal Auctions with Budgets","authors":"Zhe Feng, Harikrishna Narasimhan, David C Parkes","year":"2018","venue":"Proceedings of the 17th International Conference on Autonomous Agents and Multiagent Systems","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Fotakis and Tzamos, 2014] Dimitris Fotakis and Christos Tzamos. On the power of deterministic mechanisms for facility location games. ACM Transactions on Economics and Computation, 2(4):15, 2014.","title":"On the power of deterministic mechanisms for facility location games","authors":"Dimitris Fotakis, Christos Tzamos","year":"2014","venue":"ACM Transactions on Economics and Computation","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Gibbard, 1973] Allan Gibbard. Manipulation of voting schemes: a general result. Econometrica, 41(4):587-601, 1973.","title":"Manipulation of voting schemes: a general result","authors":"Allan Gibbard, Gibbard","year":"1973","venue":"Econometrica","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Heo, 2013] Eun Jeong Heo. Strategy-proof rules for two public goods: double median rules. Social Choice and Welfare, 41(4):895-922, 2013.","title":"Strategy-proof rules for two public goods: double median rules","authors":"Eun Jeong, Heo","year":"2013","venue":"Social Choice and Welfare","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Lu et al., 2010] Pinyan Lu, Xiaorui Sun, Yajun Wang, and Zeyuan Allen Zhu. Asymptotically Optimal Strategy- proof Mechanisms for Two-facility Games. In Proceed- ings of the 11th ACM Conference on Electronic Com- merce. ACM, 2010.","title":"Asymptotically Optimal Strategyproof Mechanisms for Two-facility Games","authors":"Pinyan Lu, Xiaorui Sun, Yajun Wang, Zeyuan Allen, Zhu","year":"2010","venue":"Proceedings of the 11th ACM Conference on Electronic Commerce","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Morgenstern and Roughgarden, 2016] Jamie Morgenstern and Tim Roughgarden. Learning Simple Auctions. In Pro- ceedings of the Conference on Learning Theory, 2016.","title":"Learning Simple Auctions","authors":"Jamie Morgenstern, Tim Roughgarden","year":"2016","venue":"Proceedings of the Conference on Learning Theory","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Moulin, 1980] H Moulin. On strategy-proofness and single- peakedness. Public Choice, 35(4):55-74, 1980.","title":"On strategy-proofness and singlepeakedness","authors":"Moulin","year":"1980","venue":"Public Choice","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Narasimhan and Parkes, 2016] Harikrishna Narasimhan and David C. Parkes. A general statistical framework for designing strategy-proof assignment mechanisms. In Proceedings of the Thirty-Second Conference on Uncertainty in Artificial Intelligence, 2016.","title":"A general statistical framework for designing strategy-proof assignment mechanisms","authors":"Harikrishna Narasimhan, David C Parkes","year":"2016","venue":"Proceedings of the Thirty-Second Conference on Uncertainty in Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Narasimhan et al., 2016] H. Narasimhan, S. Agarwal, and D. C. Parkes. Automated mechanism design without money via machine learning. In Proceedings of the 25th International Joint Conference on Artificial Intelligence, 2016.","title":"Automated mechanism design without money via machine learning","authors":"H Narasimhan, S Agarwal, D C Parkes","year":"2016","venue":"Proceedings of the 25th International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2016/68"},{"position":20,"raw":"[Nocedal and Wright, 1999] Jorge Nocedal and Stephen Wright. Numerical optimization. Springer, 1999.","title":"Numerical optimization","authors":"Jorge Nocedal, Stephen Wright","year":"1999","venue":null,"doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Procaccia and Tennenholtz, 2013] Ariel D. Procaccia and Moshe Tennenholtz. Approximate Mechanism Design without Money. ACM Transactions on Economics and Computation, 1(4):1-26, 2013.","title":"Approximate Mechanism Design without Money","authors":"Ariel D Procaccia, Moshe Tennenholtz","year":"2013","venue":"ACM Transactions on Economics and Computation","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Procaccia et al., 2009] A.D. Procaccia, A.Zohar, Y. Peleg, and J.S. Rosenschein. The learnability of voting rules. Ar- tificial Intelligence, 173:1133-1149, 2009.","title":"The learnability of voting rules","authors":"A D Procaccia, A Zohar, Y Peleg, J S Rosenschein","year":"2009","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Satterthwaite, 1975] Mark Allen Satterthwaite. Strategy- proofness and Arrow's conditions: Existence and corre- spondence theorems for voting procedures and social wel- fare functions. Journal of economic theory, 10(2):187- 217, 1975.","title":"Strategyproofness and Arrow's conditions: Existence and correspondence theorems for voting procedures and social welfare functions","authors":"Mark Allen, Satterthwaite","year":"1975","venue":"Journal of economic theory","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Sill, 1998] Joseph Sill. Monotonic networks. In Advances in Neural Information Processing Systems, 1998.","title":"Monotonic networks","authors":"Joseph Sill","year":"1998","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Sui et al., 2013] Xin Sui, Craig Boutilier, and Tuomas W. Sandholm. Analysis and optimization of multi- dimensional percentile mechanisms. In Proceedings of the 27th AAAI Conference on Artificial Intelligence, 2013.","title":"Analysis and optimization of multidimensional percentile mechanisms","authors":"Xin Sui, Craig Boutilier, Tuomas W Sandholm","year":"2013","venue":"Proceedings of the 27th AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wang and Lu, 2009] Yajun Wang and Pinyan Lu. Tighter Bounds for Facility Games. In Proceedings of the 5th International Workshop on Internet and Network Eco- nomics, 2009.","title":"Tighter Bounds for Facility Games","authors":"Wang, Lu ; ] Yajun Wang, Pinyan Lu","year":"2009","venue":"Proceedings of the 5th International Workshop on Internet and Network Economics","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Xia, 2013] Lirong Xia. Designing social choice mecha- nisms using machine learning. In Proceedings of the in- ternational conference on Autonomous agents and multi- agent systems, 2013.","title":"Designing social choice mechanisms using machine learning","authors":"Lirong Xia","year":"2013","venue":"Proceedings of the international conference on Autonomous agents and multiagent systems","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}