In many real‐world applications, designs can only be evaluated pairwise, relative to each
other. Nevertheless, in the simulation literature, almost all the ranking and selection …

This paper is concerned with the problem of top-K ranking from pairwise comparisons. Given
a collection of n items and a few pairwise comparisons across them, one wishes to identify …

Active ranking from pairwise comparisons and when parametric assumptions do not help Page
1 The Annals of Statistics 2019, Vol. 47, No. 6, 3099–3126 https://doi.org/10.1214/18-AOS1772 …

Crowdsourcing has gained immense popularity in machine learning applications for
obtaining large amounts of labeled data. Crowdsourcing is cheap and fast, but suffers from …

The supplement [5] includes all the technical proofs. In Appendix A, we first give proofs for all
the results established in Section 4: Theorem 4.1, Theorem 4.2 and Theorem 4.3. After that …

The supplement [10] includes all the technical proofs. In Appendix A, we first give the proof
of Theorem 3.1. In Appendix B, we give the proof of Theorem 4.1. After that, we prove …

We study the active learning problem of top-k ranking from multi-wise comparisons under
the popular multinomial logit model. Our goal is to identify the top-k items with high …

We introduce the probably approximately correct (PAC)\emph {Battling-Bandit} problem with
the Plackett-Luce (PL) subset choice model–an online learning framework where at each …

We address the problem of convex optimization with preference feedback, where the goal is
to minimize a convex function given a weaker form of comparison queries. Each query …

Consider the following abstract coin tossing problem: Given a set of n coins with unknown
biases, find the most biased coin using a minimal number of coin tosses. This is a common …