Generalization Bounds for k-Partite Ranking
نویسندگان
چکیده
We study generalization properties of ranking algorithms in the setting of the k-partite ranking problem. In the k-partite ranking problem, one is given examples of instances labeled with one of k ordered ‘ratings’, and the goal is to learn from these examples a real-valued ranking function that ranks instances in accordance with their ratings. This form of ranking problem arises naturally in a variety of applications and, formally, constitutes a generalization of the bipartite ranking problem that has recently been studied. We start by defining notions of ranking error suitable for measuring the quality of a ranking function in the k-partite setting. We then give distribution-free probabilistic bounds on the expected error of a ranking function learned by a k-partite ranking algorithm.
منابع مشابه
Stability and Generalization of Bipartite Ranking Algorithms
The problem of ranking, in which the goal is to learn a real-valued ranking function that induces a ranking or ordering over an instance space, has recently gained attention in machine learning. We study generalization properties of ranking algorithms, in a particular setting of the ranking problem known as the bipartite ranking problem, using the notion of algorithmic stability. In particular,...
متن کاملUnmixed $r$-partite graphs
Unmixed bipartite graphs have been characterized by Ravindra and Villarreal independently. Our aim in this paper is to characterize unmixed $r$-partite graphs under a certain condition, which is a generalization of Villarreal's theorem on bipartite graphs. Also, we give some examples and counterexamples in relevance to this subject.
متن کاملTight Approximation Bounds for Vertex Cover on Dense k-Partite Hypergraphs
We establish almost tight upper and lower approximation bounds for the Vertex Cover problem on dense k-partite hypergraphs.
متن کاملMatchings and Tilings in Hypergraphs
We consider two extremal problems in hypergraphs. First, given k ≥ 3 and k-partite k-uniform hypergraphs, as a generalization of graph (k = 2) matchings, we determine the partite minimum codegree threshold for matchings with at most one vertex left in each part, thereby answering a problem asked by Rödl and Ruciński. We further improve the partite minimum codegree conditions to sum of all k par...
متن کاملGeneralization Bounds for Ranking Algorithms via Algorithmic Stability
The problem of ranking, in which the goal is to learn a real-valued ranking function that induces a ranking or ordering over an instance space, has recently gained much attention in machine learning. We study generalization properties of ranking algorithms using the notion of algorithmic stability; in particular, we derive generalization bounds for ranking algorithms that have good stability pr...
متن کامل