Strategyproof classification

Reshef Meir; Jeffrey S. Rosenschein

doi:10.1145/2325702.2325708

Strategyproof classification

Reshef Meir, Jeffrey S. Rosenschein

The Rachel and Selim Benin School of Engineering and Computer Science

Research output: Contribution to journal › Article › peer-review

Abstract

Experts reporting the labels used by a learning algorithm cannot always be assumed to be truthful. We describe recent advances in the design and analysis of strategyproof mechanisms for binary classification, and their relation to other mechanism design problems.

Original language	English
Pages (from-to)	21-25
Number of pages	5
Journal	ACM SIGecom Exchanges
Volume	10
Issue number	3
DOIs	https://doi.org/10.1145/2325702.2325708
State	Published - Dec 2011

Keywords

Algorithms
Theory
Economics
Mechanism design
Classification
Game theory

Access to Document

10.1145/2325702.2325708License: Unspecified

Cite this

@article{d0a4860f7eaa40069bdcd0fd7de87ac3,

title = "Strategyproof classification",

abstract = "Experts reporting the labels used by a learning algorithm cannot always be assumed to be truthful. We describe recent advances in the design and analysis of strategyproof mechanisms for binary classification, and their relation to other mechanism design problems.",

keywords = "Algorithms, Theory, Economics, Mechanism design, Classification, Game theory",

author = "Reshef Meir and Rosenschein, {Jeffrey S.}",

year = "2011",

month = dec,

doi = "10.1145/2325702.2325708",

language = "אנגלית",

volume = "10",

pages = "21--25",

journal = "ACM SIGecom Exchanges",

issn = "1551-9031",

publisher = "Association for Computing Machinery",

number = "3",

}

TY - JOUR

T1 - Strategyproof classification

AU - Meir, Reshef

AU - Rosenschein, Jeffrey S.

PY - 2011/12

Y1 - 2011/12

N2 - Experts reporting the labels used by a learning algorithm cannot always be assumed to be truthful. We describe recent advances in the design and analysis of strategyproof mechanisms for binary classification, and their relation to other mechanism design problems.

AB - Experts reporting the labels used by a learning algorithm cannot always be assumed to be truthful. We describe recent advances in the design and analysis of strategyproof mechanisms for binary classification, and their relation to other mechanism design problems.

KW - Algorithms

KW - Theory

KW - Economics

KW - Mechanism design

KW - Classification

KW - Game theory

U2 - 10.1145/2325702.2325708

DO - 10.1145/2325702.2325708

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

SN - 1551-9031

VL - 10

SP - 21

EP - 25

JO - ACM SIGecom Exchanges

JF - ACM SIGecom Exchanges

IS - 3

ER -

Strategyproof classification

Abstract

Keywords

Access to Document

Fingerprint

Cite this