论文信息 - Inference with the Universum

Inference with the Universum

In this paper we study a new framework introduced by Vapnik (1998) and Vapnik (2006) that is an alternative capacity concept to the large margin approach. In the particular case of binary classification, we are given a set of labeled examples, and a collection of "non-examples" that do not belong to either class of interest. This collection, called the Universum, allows one to encode prior knowledge by representing meaningful concepts in the same domain as the problem at hand. We describe an algorithm to leverage the Universum by maximizing the number of observed contradictions, and show experimentally that this approach delivers accuracy improvements over using labeled data alone.

[1] John Shawe-Taylor,et al. Structural Risk Minimization Over Data-Dependent Hierarchies , 1998, IEEE Trans. Inf. Theory.

[2] Tomaso Poggio,et al. Incorporating prior information in machine learning by creating virtual examples , 1998, Proc. IEEE.

[3] Yiming Yang,et al. RCV1: A New Benchmark Collection for Text Categorization Research , 2004, J. Mach. Learn. Res..

[4] Masao Fukushima,et al. A new multi-class support vector algorithm , 2006, Optim. Methods Softw..

[5] Bernhard Schölkopf,et al. Incorporating Invariances in Support Vector Learning Machines , 1996, ICANN.

[6] Henry S. Baird,et al. Document image defect models , 1995 .

[7] Vladimir N. Vapnik,et al. The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[8] Vladimir Vapnik,et al. Statistical learning theory , 1998 .

[9] V. Vapnik. Estimation of Dependences Based on Empirical Data , 2006 .

[10] O. Mangasarian. Linear and Nonlinear Separation of Patterns by Linear Programming , 1965 .

[11] Bernhard E. Boser,et al. A training algorithm for optimal margin classifiers , 1992, COLT '92.

[12] Todd K. Leen,et al. From Data Distributions to Regularization in Invariant Learning , 1995, Neural Computation.

[13] Yves Grandvalet,et al. Noise Injection: Theoretical Prospects , 1997, Neural Computation.