Efficient Ranking from Pairwise Comparisons — Supplementary Material —
ثبت نشده
چکیده
In this section we will show that the SVM, applied to ranking (as described in Section 3) has an O(n) sample complexity. A related claim (without complete proof) has been made in (Radinsky & Ailon, 2011). We then show that this sample complexity is tight. Proposition 3.1. There is a constant d, so that for any 0 < η < 1, if we noiselessly measure dn/η binary comparisons, chosen uniformly at random with replacement, and n > n0 is large enough, the SVM will produce a prediction π̂, which satisfies
منابع مشابه
Passive and Active Ranking from Pairwise Comparisons
In the problem of ranking from pairwise comparisons, the learner has access to pairwise preferences among n objects and is expected to output a total order of these objects. This problem has a wide range of applications not only in computer science but also in other areas such as social science and economics. In this report, we will give a survey of passive and active learning algorithms for ra...
متن کاملThe separation, and separation-deviation methodology for group decision making and aggregate Ranking
In a generic group decision scenario, the decision makers review alternatives and then provide their own individual ranking. The aggregate ranking problem is to obtain a ranking that is fair and representative of the individual rankings. We argue here that using cardinal pairwise comparisons provides several advantages over score-wise models. The aggregate group ranking problem is then formaliz...
متن کاملThe Separation, and Separation-Deviation Methodology
In a generic group decision scenario, the decision makers review alternatives and then provide their own individual ranking. The aggregate ranking problem is to obtain a ranking that is fair and representative of the individual rankings. We argue here that using cardinal pairwise comparisons provides several advantages over scorewise models. The aggregate group ranking problem is then formalize...
متن کاملEfficient Ranking from Pairwise Comparisons
The ranking of n objects based on pairwise comparisons is a core machine learning problem, arising in recommender systems, ad placement, player ranking, biological applications and others. In many practical situations the true pairwise comparisons cannot be actively measured, but a subset of all n(n−1)/2 comparisons is passively and noisily observed. Optimization algorithms (e.g., the SVM) coul...
متن کاملActive Ranking using Pairwise Comparisons
This paper examines the problem of ranking a collection of objects using pairwise comparisons (rankings of two objects). In general, the ranking of n objects can be identified by standard sorting methods using n log2 n pairwise comparisons. We are interested in natural situations in which relationships among the objects may allow for ranking using far fewer pairwise comparisons. Specifically, w...
متن کامل