• Corpus ID: 18811574

Multicategory Support Vector Machines, Theory, and Application to the Classification of . . .

@inproceedings{Lin2003MulticategorySV,
  title={Multicategory Support Vector Machines, Theory, and Application to the Classification of . . .},
  author={Yi Lin},
  year={2003}
}

Figures from this paper

Leveraged Weighted Loss For Partial Label Learning (Supplementary Material)
TLDR
In order to achieve the risk consistency result for the LW loss in Theorem 1, it is shown that the partial loss function L̄(~y, g(x)), under the generalized assumption that partial label sets follows the label-specific sampling, is risk-consistent with respect to the supervised loss function.
Output-Tracking Quantized Explicit Nonlinear Model Predictive Control Using Multiclass Support Vector Machines
TLDR
A systematic data-driven method is proposed for the design of quantized EMPCs (Q-EMPCs) for time-varying output tracking in nonlinear systems and extensive testing and comparison among the different MC-SVM algorithms is performed to demonstrate the effectiveness and scalability.
Multicategory large-margin unified machines
TLDR
A new Multicategory LUM (MLUM) framework is proposed to investigate the behavior of soft versus hard classification under multicategory settings and its transition behavior from soft to hard classifiers and the theoretical and numerical results suggest that the proposed tuned MLUM yields very competitive performance.
Margin and Domain Integrated Classification for Images
TLDR
In this paper, a novel approach called margin and domain integrated classifier (MDIC) is addressed, which merges the conventional support vector machine and support vector domain description classifiers, and handles multi-class problems as a combination of several target classes plus outliers.
Sparse supervised dimension reduction in high dimensional classification
The original source for this publication is at the Institute of Mathematical Statistics; DOI: 10.1214/10-EJS572
Utility-based Weighted Multicategory Robust Support Vector Machines.
TLDR
It is shown that surprisingly, the cost- based weights do not work well for weighted extensions of the RSVM, and a novel utility-based weights for the weighted RSVM is proposed, as an extension of the standard SVM.
NO . 1155 September 4 , 2009 Encoding Dissimilarity Data for Statistical Model Building
TLDR
This work summarizes, review and comment upon three papers which discuss the use of discrete, noisy, incomplete, scattered pairwise dissimilarity data in statistical model building, and proposes a framework for kernel regularization with application to protein clustering.
Variable selection for the multicategory SVM via adaptive sup-norm regularization
TLDR
This paper proposes two novel types of regularization in the context of the multicategory SVM for simultaneous classification and variable selection, which lead to sparse multi-classifiers with enhanced interpretability and improved accuracy, especially for high dimensional low sample size data.
A Framework for Kernel-Based Multi-Category Classification
TLDR
A geometric framework for understanding multi-category classification is introduced, through which many existing 'all-together' algorithms can be understood, and how this architecture provides insights regarding how to further improve on the speed of existing multi- category classification algorithms is described.
Gene Expression-Based Glioma Classification Using Hierarchical Bayesian Vector Machines
TLDR
It is shown that the proposed Bayesian classification models with multiple shrinkage parameters can produce more accurate classification scheme for the glioma cancer compared to several existing classical methods.
...
...

References

SHOWING 1-10 OF 12 REFERENCES
Support ve tor ma hines and the Bayes rule in lassi ation ,
  • Data Mining andKnowledge Dis overy
  • 2002
Regularization Networks and Support Vector Machines
TLDR
Both formulations of regularization and Support Vector Machines are reviewed in the context of Vapnik's theory of statistical learning which provides a general foundation for the learning problem, combining functional analysis and statistics.
Support ve tor ma hines for multi lass pattern re ognition , Pro eedings of the Seventh European Symposium On Arti ial Neural Networks
  • 1999
Pairwise neural network lassi ers withprobabilisti outputs
  • 1995
Classi ation and diagnosti predi tion of an ers using gene expression pro ling and arti ial neural networks
  • Nature Medi ine
  • 2001
Support ve tor ma hines for lassi ation in nonstandardsituations
  • Ma hine Learning
  • 2002
Classi ation by pairwise oupling
  • 1998
Soft and hard lassi ation by reprodu ing kernel Hilbert spa e methods
  • National A ademy of S ien es
  • 2002
Comparison of dis rimination methods for the lassi ation of tumors using gene expression data
  • Journal of the Ameri an Statisti al Asso iation
  • 2002
...
...