Calibration and regret bounds for order-preserving surrogate losses in learning to rank

摘要

Learning to rank is usually reduced to learning to score individual objects, leaving the “ranking” step to a sorting algorithm. In that context, the surrogate loss used for training the scoring function needs to behave well with respect to the target performance measure which only sees the final ranking. A characterization of such a good behavior is the notion of calibration, which guarantees that minimizing (over the set of measurable functions) the surrogate risk allows us to maximize the true performance.