Paper Title:
Generalization Bounds for Certain Class of Ranking Algorithm
  Abstract

The quality of ranking determines the success or failure of information retrieval and the goal of ranking is to learn a real-valued ranking function that induces a ranking or ordering over an instance space. We focus on a ranking setting which uses truth function to label each pair of instances and the ranking preferences are given randomly from some distributions on the set of possible undirected edge sets of a graph. The contribution of this paper is the given generalization bounds for such ranking algorithm via strong and weak stability. Such stabilities have lower demand than uniform stability and fit for more real applications.

  Info
Periodical
Edited by
Yanwen Wu
Pages
456-461
DOI
10.4028/www.scientific.net/AMR.267.456
Citation
W. Gao, Y. G. Zhang, "Generalization Bounds for Certain Class of Ranking Algorithm", Advanced Materials Research, Vol. 267, pp. 456-461, 2011
Online since
June 2011
Export
Price
$32.00
Share

In order to see related information, you need to Login.

In order to see related information, you need to Login.

Authors: Gui Xiang Wang, Guang Tao Zhou
Chapter 17: Signal and Intelligent Information Processing
Abstract:In this paper, a novel approach to ranking fuzzy numbers based on the mean and the fuzzy degree of fuzzy number is proposed. In the approach,...
2102
Authors: Wei Gao, Tian Wei Xu, Li Liang, Jian Hou Gan
Chapter 9: Information Technologies, Communication and Networks
Abstract:Ontology similarity calculation and ontology mapping are crucial research topics in information retrieval. Ontology, as a concept structure...
1051
Authors: Jin Luo
Chapter 3: Numerical Methods, Computation Methods and Algorithms for Modeling, Simulation and Optimization, Data Mining and Data Processing
Abstract:Ranking data points with respect to a given preference criterion is an example of a preference learning task. In this paper, we investigate...
2286