A few notes on statistical learning theory
Advanced lectures on machine learning
Rademacher and gaussian complexities: risk bounds and structural results
The Journal of Machine Learning Research
An efficient boosting algorithm for combining preferences
The Journal of Machine Learning Research
Learning to rank: from pairwise approach to listwise approach
Proceedings of the 24th international conference on Machine learning
Query-level loss functions for information retrieval
Information Processing and Management: an International Journal
Query-level stability and generalization in learning to rank
Proceedings of the 25th international conference on Machine learning
Listwise approach to learning to rank: theory and algorithm
Proceedings of the 25th international conference on Machine learning
Stability and generalization of bipartite ranking algorithms
COLT'05 Proceedings of the 18th annual conference on Learning Theory
Rademacher averages and phase transitions in Glivenko-Cantelli classes
IEEE Transactions on Information Theory
Learning to Rank for Information Retrieval
Foundations and Trends in Information Retrieval
Ranking from pairs and triplets: information quality, evaluation methods and query complexity
Proceedings of the fourth ACM international conference on Web search and data mining
RankDE: learning a ranking function for information retrieval using differential evolution
Proceedings of the 13th annual conference on Genetic and evolutionary computation
Cost-Sensitive listwise ranking approach
PAKDD'10 Proceedings of the 14th Pacific-Asia conference on Advances in Knowledge Discovery and Data Mining - Volume Part I
Effect on generalization of using relational information in list-wise algorithms
ICPCA/SWS'12 Proceedings of the 2012 international conference on Pervasive Computing and the Networked World
Hi-index | 0.00 |
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 learning-to-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 tightness of the bounds in different situations with regard to the list length and transformation function.