We introduce a gradient descent algorithm for bipartite ranking with general convex losses. The implementation of this algorithm is simple, and its generalization performance is investigated. Explicit learning rates are presented in terms of the suitable choices of the regularization parameter and the step size. The result fills the theoretical gap in learning rates for ranking problem with general convex losses.
"Approximation Analysis of Gradient Descent Algorithm for Bipartite Ranking." J. Appl. Math. 2012 1 - 13, 2012. https://doi.org/10.1155/2012/189753