Empirical Study of the Universum SVM Learning for High-Dimensional Data

Authors:
Vladimir Cherkassky;Wuyang Dai
Affiliations:
Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, USA 55455;Department of Electrical and Computer Engineering, University of Minnesota, Minneapolis, USA 55455
Venue:
ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I
Year:
2009

Citing 3
Cited 0

Inference with the Universum

ICML '06 Proceedings of the 23rd international conference on Machine learning
Estimation of Dependences Based on Empirical Data: Empirical Inference Science (Information Science and Statistics)

Estimation of Dependences Based on Empirical Data: Empirical Inference Science (Information Science and Statistics)
Learning from Data: Concepts, Theory, and Methods

Learning from Data: Concepts, Theory, and Methods

Quantified Score

Hi-index	0.00

Visualization

Abstract

Many applications of machine learning involve sparse high-dimensional data, where the number of input features is (much) larger than the number of data samples, d *** n . Predictive modeling of such data is very ill-posed and prone to overfitting. Several recent studies for modeling high-dimensional data employ new learning methodology called Learning through Contradictions or Universum Learning due to Vapnik (1998,2006). This method incorporates a priori knowledge about application data, in the form of additional Universum samples, into the learning process. This paper investigates generalization properties of the Universum-SVM and how they are related to characteristics of the data. We describe practical conditions for evaluating the effectiveness of Random Averaging Universum.