Multi-dueling bandits and their application to online ranker evaluation

Publikation: Bidrag til bog/antologi/rapportKonferencebidrag i proceedingsForskningfagfællebedømt

New ranking algorithms are continually being developed and refined, necessitating the development of efficient methods for evaluating these rankers. Online ranker evaluation focuses on the challenge of efficiently determining, from implicit user feedback, which ranker out of a finite set of rankers is the best. Online ranker evaluation can be modeled by dueling ban- dits, a mathematical model for online learning under limited feedback from pairwise comparisons. Comparisons of pairs of rankers is performed by interleaving their result sets and examining which documents users click on. The dueling bandits model addresses the key issue of which pair of rankers to compare at each iteration, thereby providing a solution to the exploration-exploitation trade-off. Recently, methods for simultaneously comparing more than two rankers have been developed. However, the question of which rankers to compare at each iteration was left open. We address this question by proposing a generalization of the dueling bandits model that uses simultaneous comparisons of an unrestricted number of rankers. We evaluate our algorithm on synthetic data and several standard large-scale online ranker evaluation datasets. Our experimental results show that the algorithm yields orders of magnitude improvement in performance compared to stateof- the-art dueling bandit algorithms.
TitelProceedings of the 25th ACM International Conference on Information and Knowledge Management
Antal sider6
ForlagAssociation for Computing Machinery
ISBN (Elektronisk)978-1-4503-4073-1
StatusUdgivet - 2016
Begivenhed25th ACM International Conference on Information and Knowledge Management - Indianapolis, USA
Varighed: 24 okt. 201628 okt. 2016
Konferencens nummer: 25


Konference25th ACM International Conference on Information and Knowledge Management
NavnACM International Conference on Information and Knowledge Management


  • cs.IR, cs.LG, stat.ML

ID: 167579172