How to learn large posets by pairwise comparisons
نویسنده
چکیده
The expected number of pairwise comparisons needed to learn a partial order on n elements is shown to be at least n/4 − o(n), and an algorithm is given that needs only n/4 + o(n) comparisons on average. In addition, the optimal strategy for learning a poset with four elements is presented.
منابع مشابه
The asymptotic complexity of partial sorting -- How to learn large posets by pairwise comparisons
The expected number of pairwise comparisons needed to learn a partial order on n elements is shown to be at least n/4 − o(n), and an algorithm is given that needs only n/4 + o(n) comparisons on average. In addition, the optimal strategy for learning a poset with four elements is presented.
متن کاملRecommendation from Intransitive Pairwise Comparisons
In this paper we propose a full Bayesian probabilistic method to learn preferences from non-transitive pairwise comparison data. Such lack of transitivity easily arises when the number of pairwise comparisons is large, and they are given sequentially without allowing for consistency check. We develop a Bayesian Mallows model able to handle such data through a latent layer of uncertainty which c...
متن کاملLearning Combinatorial Functions from Pairwise Comparisons
A large body of work in machine learning has focused on the problem of learning a close approximation to an underlying combinatorial function, given a small set of labeled examples. However, for real-valued functions, cardinal labels might not be accessible, or it may be difficult for an expert to consistently assign real-valued labels over the entire set of examples. For instance, it is notori...
متن کاملPosets on up to 16 Points
In this article we describe a very efficient method to construct pairwise nonisomorphic posets (equivalently, T0 topologies). We also give the results obtained by a computer program based on this algorithm, in particular the numbers of nonisomorphic posets on 15 and 16 points and the numbers of labelled posets and topologies on 17 and 18 points.
متن کاملLearning Mixed Membership Mallows Models from Pairwise Comparisons
We propose a novel parameterized family of Mixed Membership Mallows Models (M4) to account for variability in pairwise comparisons generated by a heterogeneous population of noisy and inconsistent users. M4 models individual preferences as a user-specific probabilistic mixture of shared latent Mallows components. Our key algorithmic insight for estimation is to establish a statistical connectio...
متن کامل