R. Herbrich, T. Graepel, and K. Obermayer (2000)
Large Margin Rank Boundaries for Ordinal Regression
In: Advances in Large Margin Classifiers, ed. by A.J. Smola and P.L. Bartlett and B. Schölkopf and D. Schuurmans, pp. 115-132, Cambridge, MA, MIT Press.
Based on ideas from SV classification an algorithm is designed to obtain Large Margin Rank Boundaries for Ordinal Regression. In other words, a SV algorithm for learning preference relations. In addition to that, the paper contains a detailed derivation of the corresponding cost functions, risk functionals, and proves uniform convergence bounds for the setting. Experimental evidence shows the good performance of their distribution independent approach.