Incentive compatible regression learning

DOI10.1016/J.JCSS.2010.03.003MaRDI QIDQ1959425zbMATH OpenOpenAlexFDO

Authors Ofer Dekel, Felix Fischer, Ariel D. Procaccia

Publication date 7 October 2010

Published in Journal of Computer and System Sciences (Search for Journal in Brave)

Full work available at URL https://drops.dagstuhl.de/opus/volltexte/2007/1162/

zbMATH Keywords

regression analysisalgorithmic mechanism designcomputational learning theory

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Computational learning theory (68Q32) Rationality and learning in game theory (91A26)

Recommendations

• Reducing mechanism design to algorithm design via machine learning
• On incentive-compatible estimators
• Is privacy compatible with truthfulness?
• Algorithms for strategyproof classification
• Bayesian algorithmic mechanism design

Cites work

• scientific article; zbMATH DE number 5343724 (Why is no real title available?)
• 10.1162/153244303321897690
• Algorithmic mechanism design
• Can PAC learning algorithms tolerate random attribute noise?
• Convergence of stochastic processes
• Decision theoretic generalizations of the PAC model for neural net and other learning applications
• Generalized Condorcet-winners for single peaked and single-plateau preferences
• Incentives in Teams
• Inventory management of a fast-fashion retail network
• Learnability and rationality of choice.
• Learning in the Presence of Malicious Errors
• Manipulation of Voting Schemes: A General Result
• Microeconomic theory
• PAC learning with nasty noise.
• Reducing mechanism design to algorithm design via machine learning
• Straightforward Elections, Unanimity and Phantom Voters
• Strategy-proof estimators for simple regression.
• Strategy-proofness and Arrow's conditions: existence and correspondence theorems for voting procedures and social welfare functions
• The learnability of voting rules
• Thirteen Reasons Why the Vickrey-Clarke-Groves Process Is Not Practical
• Truth revelation in approximately efficient combinatorial auctions
• Truthful randomized mechanisms for combinatorial auctions

Cited in

(14)

• On incentive-compatible estimators
• Optimal impartial selection
• Decomposing the output gap with inflation learning
• A mechanism design approach for multi-party machine learning
• Incentive Compatible Active Learning.
• Regression markets and application to energy forecasting
• Computational principal-agent problems
• Parametric prediction from parametric agents
• GOODHART'S LAW AND MACHINE LEARNING: A STRUCTURAL PERSPECTIVE
• A survey on approximation mechanism design without money for facility games
• Optimally Deceiving a Learning Leader in Stackelberg Games
• On classification of strategic agents who can both game and improve
• Algorithms for strategyproof classification
• A mechanism design approach for multi-party machine learning

This page was built for publication: Incentive compatible regression learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1959425)