Communications of the ACM
An introduction to computational learning theory
An introduction to computational learning theory
Theoretical Computer Science
Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining
An Algorithm for Automatically Designing Deterministic Mechanisms without Payments
AAMAS '04 Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems - Volume 1
Mechanism Design via Machine Learning
FOCS '05 Proceedings of the 46th Annual IEEE Symposium on Foundations of Computer Science
Good learners for evil teachers
ICML '09 Proceedings of the 26th Annual International Conference on Machine Learning
The learnability of voting rules
Artificial Intelligence
Approximate mechanism design without money
Proceedings of the 10th ACM conference on Electronic commerce
Proceedings of the 10th ACM conference on Electronic commerce
Strategyproof classification under constant hypotheses: a tale of two functions
AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 1
Competitive Repeated Allocation without Payments
WINE '09 Proceedings of the 5th International Workshop on Internet and Network Economics
Proceedings of the 11th ACM conference on Electronic commerce
Asymptotically optimal strategy-proof mechanisms for two-facility games
Proceedings of the 11th ACM conference on Electronic commerce
Truthful assignment without money
Proceedings of the 11th ACM conference on Electronic commerce
On the limits of dictatorial classification
Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: volume 1 - Volume 1
Finding approximate competitive equilibria: efficient and fair course allocation
Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: volume 1 - Volume 1
Strategy-proof allocation of multiple items between two agents without payments or priors
Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: volume 1 - Volume 1
Incentive compatible regression learning
Journal of Computer and System Sciences
Tight bounds for strategyproof classification
The 10th International Conference on Autonomous Agents and Multiagent Systems - Volume 1
SAGT'11 Proceedings of the 4th international conference on Algorithmic game theory
Complexity of mechanism design
UAI'02 Proceedings of the Eighteenth conference on Uncertainty in artificial intelligence
Approximate judgement aggregation
WINE'11 Proceedings of the 7th international conference on Internet and Network Economics
Mechanism design on discrete lines and cycles
Proceedings of the 13th ACM Conference on Electronic Commerce
Mechanism design on discrete lines and cycles
Proceedings of the 13th ACM Conference on Electronic Commerce
Multiagent systems, and the search for appropriate foundations
Proceedings of the 2013 international conference on Autonomous agents and multi-agent systems
Approximate Mechanism Design without Money
ACM Transactions on Economics and Computation
Hi-index | 0.00 |
The strategyproof classification problem deals with a setting where a decision maker must classify a set of input points with binary labels, while minimizing the expected error. The labels of the input points are reported by self-interested agents, who might lie in order to obtain a classifier that more closely matches their own labels, thereby creating a bias in the data; this motivates the design of truthful mechanisms that discourage false reports. In this paper we give strategyproof mechanisms for the classification problem in two restricted settings: (i) there are only two classifiers, and (ii) all agents are interested in a shared set of input points. We show that these plausible assumptions lead to strong positive results. In particular, we demonstrate that variations of a random dictator mechanism, that are truthful, can guarantee approximately optimal outcomes with respect to any family of classifiers. Moreover, these results are tight in the sense that they match the best possible approximation ratio that can be guaranteed by any truthful mechanism. We further show how our mechanisms can be used for learning classifiers from sampled data, and provide PAC-style generalization bounds on their expected error. Interestingly, our results can be applied to problems in the context of various fields beyond classification, including facility location and judgment aggregation.