Simple Risk Bounds for Position-Sensitive Max-Margin Ranking Algorithms
Stefan Riezler, Fabio De Bona · 2009
We present risk bounds for position-sensitive max-margin ranking algorithms that follow straightforwardly from a structural result for Rademacher averages presented by [1]. We apply this result to pairwise and listwise hinge loss that are position-sensitive by virtue of rescaling the margin by a pairwise or listwise position-sensitive prediction loss. 1