As you like it: Localization via paired comparisons

Suppose that we wish to estimate a vector from a set of binary paired comparisons of the form " is closer to than to " for various choices of vectors and . The problem of estimating 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 under a randomized model for and . 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 and , 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 and .
View on arXiv