HackerPapers

arXiv:1312.3393cs.LG

Relative Upper Confidence Bound for the K-Armed Dueling Bandit Problem

Masrour Zoghi, Shimon Whiteson, Remi Munos, Maarten de Rijke

Early discovery. Linked by one identifiable commenter. This paper is outside the main ranking; a mention is not an endorsement.

Abstract

This paper proposes a new method for the K-armed dueling bandit problem, a variation on the regular K-armed bandit problem that offers only relative feedback about pairs of arms. Our approach extends the Upper Confidence Bound algorithm to the relative setting by using estimates of the pairwise probabilities to select a promising arm and applying Upper Confidence Bound with the winner as a benchmark. We prove a finite-time regret bound of order O(log t). In addition, our empirical results using real data from an information retrieval application show that it greatly outperforms the state of the art.

arXiv comments
13 pages, 6 figures
Journal reference
DOI
Subjects
cs.LGMachine Learning

On Hacker News

Linked by 1 identifiable commenter in 1 comment across 1 thread, from Jan 2015 to Jan 2015.

Comments linking this paper, per year.

Discussed in comments1 thread

  1. The multiple comparisons problem 1 comment

    • Yes, I think so. It might be of interest to you that there is now some published work on bandit algorithms for when all you have is ranking, not absolute ordering. This is close to what we were talking about: http://arxiv.org/pdf/1312.3393.pdf

      noelwelshView on HNParent context

Submitted to Hacker News

Connected through shared HN threads, not inferred similarity or a recommendation.