Generalization analysis of listwise learning-to-rank algorithms

This paper presents a theoretical framework for ranking, and demonstrates how to perform generalization analysis of listwise ranking algorithms using the framework. Many learning-to-rank algorithms have been proposed in recent years. Among them, the listwise approach has shown higher empirical ranking performance when compared to the other approaches. However, there is no theoretical study on the listwise approach as far as we know. In this paper, we propose a theoretical framework for ranking, which can naturally describe various listwise learningto-rank algorithms. With this framework, we prove a theorem which gives a generalization bound of a listwise ranking algorithm, on the basis of Rademacher Average of the class of compound functions. The compound functions take listwise loss functions as outer functions and ranking models as inner functions. We then compute the Rademacher Averages for existing listwise algorithms of ListMLE, ListNet, and RankCosine. We also discuss the tightn...

• Type: Conference
• Year: 2009
• Where: ICML
• Authors: Yanyan Lan, Tie-Yan Liu, Zhiming Ma, Hang Li
• Keywords: Compound Functions, ICML 2009, Listwise Ranking Algorithms, Machine Learning, Theoretical Framework