Ranking with Large Margin Principle: Two Approaches

By Amnon Shashua, Anat Levin. Neural Information Processing Systems, 2002

415 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/776126e58306343ef854a67c60b03bce0942a3d0

How researchers see this paper

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

Citations in the corpus

Maximum-Margin Matrix Factorization (2004, background): “On average and on three of the four test sets, MMMF achieves lower MAE than the Baseline learners; on all four of the test sets, MMMF achieves lower ZOE than the Baseline learners.”
dipIQ: Blind Image Quality Assessment by Learning-to-Rank Discriminable Image Pairs (2017, methodology): “Ordinal regression-based pointwise L2R algorithms have also been proposed such as PRanking [73] and SVM-based large margin principles [74].”
The scoring of poses in protein-protein docking: current capabilities and future directions (2013, background): “For instance, when ranking is undertaken in the pointwise approach, it can be reformulated as a classification, regression or ordinal classification problem [125-128].”
Learning to Rank for Information Retrieval and Natural Language Processing (2011, unknown): “…Subset Ranking [Cossock and Zhang, 2006]: Regression – McRank [Li et al 2007]: Multi-Class Classification Using Boosting Tree – PRank [Crammer and Singer 2002]: Ordinal Classification Using Perceptron – OC SVM [Shashua & Levin 2002]: Ordinal Classification Using SVM Learning to rank…”
Deep Ordinal Regression Network for Monocular Depth Estimation (2018, background): “For example, Shashua and Levin [53] handled multiple thresholds by developing a new SVM. Cam-mer and Singer [9] generalized the online perceptron algorithms with multiple thresholds to do ordinal regression.”
Ordinal Regression by Extended Binary Classification (2006, background): “Shashua and Levin [2] proposed new support vector machine (SVM) formulations to handle multiple thresholds.”
Multiple-instance ranking: Learning to rank images for image retrieval (2008, background): “, learning the mapping of the examples to an ordered set of numerical ranks [10, 21].”
Ordinal Regression Methods: Survey and Experimental Study (2016, methodology): “The work of Shashua and Levin [91] introduced two ﬁrst methods: the maximisation of the margin between the closest neighbouring classes and the maximisation of the sum of margins between classes.”
A Short Introduction to Learning to Rank (2011, unknown): “The method proposed by Shashua & Levin [13] utilizes a number of parallel hyperplanes as a ranking model.”
Rank consistent ordinal regression for neural networks with application to age estimation (2019, methodology): “Early work in this regard includes the use of perceptrons (Crammer and Singer, 2002; Shen and Joshi, 2005) and support vector machines (Herbrich et al., 1999; Shashua and Levin, 2003; Rajaram et al., 2003; Chu and Keerthi, 2005).”
On the Consistency of Ranking Algorithms (2010, background): “Similar losses have been proposed, e.g., by Shashua & Levin (2002).”
Optimization Models for Machine Learning: A Survey (2019, unknown): “An extension of SVM for ordinary data has been proposed in [189] and extended in [68].”
Multi-Task Learning via Conic Programming (2007, methodology): “We compare MTL-SVM(local/network)with IL-SVM, SVOR [9] (see Section 5), MTL-SVM(full/network) and MTL-SVM(global/network).”
Gaussian Processes for Ordinal Regression (2005, methodology): “Shashua and Levin (2003) generalized the formulation of support vector machines to ordinal regression and the numerical re-sults they presented shows a signiﬂcant improvement on the performance compared with the on-line algorithm proposed by Crammer and Singer (2002).”
New approaches to support vector ordinal regression (2005, methodology): “Shashua and Levin (2003) generalized the support vector formulation for ordinal regression by finding r − 1 thresholds that divide the real line into r consecutive intervals for the r ordered categories.”