In the ranking problem, one has to compare two different observations and decide the ordering between them. It has received increasing attention both in the statistical and machine learning literature. This paper considers -regularized ranking rules with convex loss. Under some mild conditions, a learning rate is established.
"Regularized Ranking with Convex Losses and -Penalty." Abstr. Appl. Anal. 2013 (SI32) 1 - 8, 2013. https://doi.org/10.1155/2013/927827