A scalable preference elicitation algorithm using group generalized binary search

Yi Ren, Clayton Scott, Panos Y. Papalambros

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

We examine the problem of eliciting the most preferred designs of a user from a finite set of designs through iterative pairwise comparisons presented to the user. The key challenge is to select proper queries (i.e., presentations of design pairs to the user) in order to minimize the number of queries. Previous work formulated elicitation as a blackbox optimization problem with comparison (binary) outputs, and a heuristic search algorithm similar to Efficient Global Optimization (EGO) was used to solve it. In this paper, we propose a query algorithm that minimizes the expected number of queries directly, assuming that designs are embedded in a known space and user preference is a linear function of design variables. Besides its theoretical foundation, the proposed algorithm shows empirical performance better than the EGO search algorithm in both simulated and real-user experiments. A novel approximation scheme is also introduced to alleviate the scalability issue of the proposed algorithm, making it tractable for a large number of design variables or of candidate designs.

Original languageEnglish (US)
Title of host publication39th Design Automation Conference
PublisherAmerican Society of Mechanical Engineers
Volume3 B
ISBN (Print)9780791855898
DOIs
StatePublished - 2013
Externally publishedYes
EventASME 2013 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE 2013 - Portland, OR, United States
Duration: Aug 4 2013Aug 7 2013

Other

OtherASME 2013 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE 2013
CountryUnited States
CityPortland, OR
Period8/4/138/7/13

Fingerprint

Binary search
Elicitation
Query
Global optimization
Global Optimization
Search Algorithm
Minimise
Pairwise Comparisons
Heuristic Search
User Preferences
Approximation Scheme
Design
Black Box
Heuristic algorithm
Linear Function
Scalability
Finite Set
Optimization Algorithm
Binary
Optimization Problem

ASJC Scopus subject areas

  • Mechanical Engineering
  • Computer Graphics and Computer-Aided Design
  • Computer Science Applications
  • Modeling and Simulation

Cite this

Ren, Y., Scott, C., & Papalambros, P. Y. (2013). A scalable preference elicitation algorithm using group generalized binary search. In 39th Design Automation Conference (Vol. 3 B). [V03BT03A005] American Society of Mechanical Engineers. https://doi.org/10.1115/DETC2013-13059

A scalable preference elicitation algorithm using group generalized binary search. / Ren, Yi; Scott, Clayton; Papalambros, Panos Y.

39th Design Automation Conference. Vol. 3 B American Society of Mechanical Engineers, 2013. V03BT03A005.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ren, Y, Scott, C & Papalambros, PY 2013, A scalable preference elicitation algorithm using group generalized binary search. in 39th Design Automation Conference. vol. 3 B, V03BT03A005, American Society of Mechanical Engineers, ASME 2013 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference, IDETC/CIE 2013, Portland, OR, United States, 8/4/13. https://doi.org/10.1115/DETC2013-13059
Ren Y, Scott C, Papalambros PY. A scalable preference elicitation algorithm using group generalized binary search. In 39th Design Automation Conference. Vol. 3 B. American Society of Mechanical Engineers. 2013. V03BT03A005 https://doi.org/10.1115/DETC2013-13059
Ren, Yi ; Scott, Clayton ; Papalambros, Panos Y. / A scalable preference elicitation algorithm using group generalized binary search. 39th Design Automation Conference. Vol. 3 B American Society of Mechanical Engineers, 2013.
@inproceedings{461918d7917f4dc594b542a19f637dd0,
title = "A scalable preference elicitation algorithm using group generalized binary search",
abstract = "We examine the problem of eliciting the most preferred designs of a user from a finite set of designs through iterative pairwise comparisons presented to the user. The key challenge is to select proper queries (i.e., presentations of design pairs to the user) in order to minimize the number of queries. Previous work formulated elicitation as a blackbox optimization problem with comparison (binary) outputs, and a heuristic search algorithm similar to Efficient Global Optimization (EGO) was used to solve it. In this paper, we propose a query algorithm that minimizes the expected number of queries directly, assuming that designs are embedded in a known space and user preference is a linear function of design variables. Besides its theoretical foundation, the proposed algorithm shows empirical performance better than the EGO search algorithm in both simulated and real-user experiments. A novel approximation scheme is also introduced to alleviate the scalability issue of the proposed algorithm, making it tractable for a large number of design variables or of candidate designs.",
author = "Yi Ren and Clayton Scott and Papalambros, {Panos Y.}",
year = "2013",
doi = "10.1115/DETC2013-13059",
language = "English (US)",
isbn = "9780791855898",
volume = "3 B",
booktitle = "39th Design Automation Conference",
publisher = "American Society of Mechanical Engineers",

}

TY - GEN

T1 - A scalable preference elicitation algorithm using group generalized binary search

AU - Ren, Yi

AU - Scott, Clayton

AU - Papalambros, Panos Y.

PY - 2013

Y1 - 2013

N2 - We examine the problem of eliciting the most preferred designs of a user from a finite set of designs through iterative pairwise comparisons presented to the user. The key challenge is to select proper queries (i.e., presentations of design pairs to the user) in order to minimize the number of queries. Previous work formulated elicitation as a blackbox optimization problem with comparison (binary) outputs, and a heuristic search algorithm similar to Efficient Global Optimization (EGO) was used to solve it. In this paper, we propose a query algorithm that minimizes the expected number of queries directly, assuming that designs are embedded in a known space and user preference is a linear function of design variables. Besides its theoretical foundation, the proposed algorithm shows empirical performance better than the EGO search algorithm in both simulated and real-user experiments. A novel approximation scheme is also introduced to alleviate the scalability issue of the proposed algorithm, making it tractable for a large number of design variables or of candidate designs.

AB - We examine the problem of eliciting the most preferred designs of a user from a finite set of designs through iterative pairwise comparisons presented to the user. The key challenge is to select proper queries (i.e., presentations of design pairs to the user) in order to minimize the number of queries. Previous work formulated elicitation as a blackbox optimization problem with comparison (binary) outputs, and a heuristic search algorithm similar to Efficient Global Optimization (EGO) was used to solve it. In this paper, we propose a query algorithm that minimizes the expected number of queries directly, assuming that designs are embedded in a known space and user preference is a linear function of design variables. Besides its theoretical foundation, the proposed algorithm shows empirical performance better than the EGO search algorithm in both simulated and real-user experiments. A novel approximation scheme is also introduced to alleviate the scalability issue of the proposed algorithm, making it tractable for a large number of design variables or of candidate designs.

UR - http://www.scopus.com/inward/record.url?scp=84896963136&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84896963136&partnerID=8YFLogxK

U2 - 10.1115/DETC2013-13059

DO - 10.1115/DETC2013-13059

M3 - Conference contribution

AN - SCOPUS:84896963136

SN - 9780791855898

VL - 3 B

BT - 39th Design Automation Conference

PB - American Society of Mechanical Engineers

ER -