BoltzRank: learning to maximize expected ranking gain

By Maksims Volkovs, Richard S. Zemel. 2009

116 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Systems

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Tie-Yan Liu
2. Tao Qin
3. Jianfeng Gao
4. Hang Li
5. Raquel Urtasun
6. Dacheng Tao
7. Mohit Bansal
8. Jimmy J. Lin

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Dacheng Tao
3. Xiaogang Wang
4. Trevor Darrell
5. Ming-Hsuan Yang
6. Jitendra Malik
7. Chunhua Shen
8. Alan L. Yuille

In Information Systems

1. Hang Li
2. Jun Xu
3. Tie-Yan Liu
4. Tao Qin
5. Yue Shi
6. Richard S. Zemel
7. R. Caruana
8. Cristina Videira Lopes

Citations in the corpus

• Bagging gradient-boosted trees for high precision, low variance ranking models (2011, methodology): “A large number of learning-to-rank algorithms have been proposed, such as [8, 7, 9, 21, 28, 30] (see [22] for a more complete list).”
• A conditional neural fields model for protein threading (2012, methodology): “CRFs and CNFs are usually trained by ML or maximum a posteriori (MAP) (Volkovs and Zemel, 2009) methods.”
• List-wise learning to rank with matrix factorization for collaborative filtering (2010, background): “CoFiRank [20] has made the first attempt to address this issue, and recent developments in this area in LTR research [10] [19] could be further exploited for improving recommendation performance by directly optimizing for evaluation metrics.”
• LETOR: A benchmark collection for research on learning to rank for information retrieval (2010, methodology): “Example algorithms include AdaRank [47], SoftRank [40], SVM-MAP [50], PermuRank [48], ApproxRank [31], and BoltzRank [43].”
• A general approximation framework for direct optimization of information retrieval measures (2010, background): “See also Qin et al. (2008c), Volkovs and Zemel (2009) for other listwise methods.”
• Training Deep Neural Networks via Direct Loss Minimization (2015, methodology): “Various efficient methods have been proposed for incorporating complex discrete loss functions into this max-margin approach (Yue et al., 2007; Volkovs & Zemel, 2009; Tarlow & Zemel, 2012; Mohapatra et al., 2014).”
• Metric Learning to Rank (2010, unknown): “Viewed in this light, we can cast nearest neighbor prediction as a ranking problem, and the predicted label error rate as a loss function over rankings.”