Support Vector Machines for Classification in Nonstandard Situations

By Yi Lin, Yoonkyung Lee, Grace Wahba. Machine-mediated learning, 2002

396 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/a6be52ea38859d6a4cf1fd7804745ddb88216e01

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

In Computer Vision and Pattern Recognition

Citations in the corpus

Robust support vector method for hyperspectral data classification and knowledge discovery (2004, methodology): “thus, no individual penalization parameter was used [49].”
Variable selection for support vector machines via smoothing spline anova (2006, positive): “Following Lin, Lee, and Wahba (2002), we define the weight w function on the label by w(+1) = c−π−π+0 and w(−1) = c +π+π−0 .”
A support vector method for optimizing average precision (2007, methodology): “Performance measures optimized include accuracy [17, 15], ROCArea [1, 5, 10, 11, 13, 21] or modifications of ROCArea [4], and NDCG [2, 3].”
How to Compare Different Loss Functions and Their Risks (2007, background): “Despite the practical importance of this learning problem only very little is known in view of the above questions (see [20] for a conjecture related to the above questions and [10] for a discussion of this learning problem).”
Cost-sensitive boosting for classification of imbalanced data (2007, methodology): “For SVMs, proposals such as using different penalty constants for different classes [58], or adjusting the class boundary based on a kernel-alignment ideal [103], are reported.”
KBA: kernel boundary alignment considering imbalanced data distribution (2005, background): “For SVMs, few attempts [16], [19], [24], [29] have dealt with the imbalanced training-data problem.”
A Literature Survey on Domain Adaptation of Statistical Classifiers (2007, methodology): “Alternatively, in the second approach, the cost or the loss of misclassifying an instance is directly re-weighted in the objective function; it will cost more to misclassify instances belonging to under-represented classes, and vice versa [Lin et al., 2002].”
A support vector method for multivariate performance measures (2005, background): “(Morik et al., 1999; Lin et al., 2002) in the context of SVMs).”
Class-Weighted Classification: Trade-offs and Robust Approaches (2020, background): “The first is class-based margin adjustment (Lin et al., 2002; Scott, 2012; Cao et al., 2019), in which the margin parameter for the margin loss function may vary by class.”
Tuning Support Vector Machines for Minimax and Neyman-Pearson Classification (2008, methodology): “We prove that this cost-sensitive SVM is equivalent to the more common 2C-SVM [7], [8], [9] and provide a careful characterization of its parameter space in Section 2.”
Multicategory Support Vector Machines, Theory, and Application to the Classiﬁcation of Microarray Data and Satellite Radiance Data (2002, neutral): “Following the usage in Lin et al. (2002), we call the case when misclassification costs are not equal or there is a sampling bias, nonstandard, as opposed to the standard case when there are equal misclassification costs without sampling bias.”
Support Vector Machines and the Bayes Rule in Classification (2002, methodology): “Lin et al. (2002) contains some extension of the SVM to such nonstandard situations.”
Class-Boundary Alignment for Imbalanced Dataset Learning (2003, background): “For SVMs, few attempts (Karakoulas & Taylor, 1999; Lin et al., 2002; Veropoulos et al., 1999) have dealt with the imbalanced training-data problem.”