资源分类
》 资源 》论文》Generalization error bounds for learning to rank: Does the length of document lists matter?

Generalization error bounds for learning to rank: Does the length of document lists matter?

2020-03-04 | |  57 |   41 |   0

Abstract

We consider the generalization ability of algorithms for learning to rank at a query level, a problem also called subset ranking. Existing generalization error bounds necessarily degrade as the size of the document list associated with a query increases. We show that such a degradation is not intrinsic to the problem. For several loss functions, including the cross-entropy loss used in the well known ListNet method, there is no degradation in generalization ability as document lists become longer. We also provide novel generalization error bounds under 图片.png regularization and faster convergence rates if the loss function is smooth.

上一篇：Trust Region Policy Optimization

下一篇：Scalable Bayesian Optimization Using Deep Neural Networks

用户评价
全部评价

热门资源

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • The Variational S...

    Unlike traditional images which do not offer in...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...