English

As you like it: Localization via paired comparisons

Machine Learning 2021-08-31 v2 Machine Learning

Abstract

Suppose that we wish to estimate a vector x\mathbf{x} from a set of binary paired comparisons of the form "x\mathbf{x} is closer to p\mathbf{p} than to q\mathbf{q}" for various choices of vectors p\mathbf{p} and q\mathbf{q}. The problem of estimating x\mathbf{x} from this type of observation arises in a variety of contexts, including nonmetric multidimensional scaling, "unfolding," and ranking problems, often because it provides a powerful and flexible model of preference. We describe theoretical bounds for how well we can expect to estimate x\mathbf{x} under a randomized model for p\mathbf{p} and q\mathbf{q}. We also present results for the case where the comparisons are noisy and subject to some degree of error. Additionally, we show that under a randomized model for p\mathbf{p} and q\mathbf{q}, a suitable number of binary paired comparisons yield a stable embedding of the space of target vectors. Finally, we also show that we can achieve significant gains by adaptively changing the distribution for choosing p\mathbf{p} and q\mathbf{q}.

Keywords

Cite

@article{arxiv.1802.10489,
  title  = {As you like it: Localization via paired comparisons},
  author = {Andrew K. Massimino and Mark A. Davenport},
  journal= {arXiv preprint arXiv:1802.10489},
  year   = {2021}
}
R2 v1 2026-06-23T00:36:54.979Z