Sample Complexity of Classifiers Taking Values in Q, Application to Multi-Class SVMs

被引：8

作者：

Guermeur, Yann ^{[1
]}

机构：

[1] LORIA, CNRS, F-54506 Vandoeuvre Les Nancy, France

来源：

COMMUNICATIONS IN STATISTICS-THEORY AND METHODS | 2010年 / 39卷 / 03期

关键词：

Generalized VC dimensions; Multi-class support vector machines; Rademacher complexity; Sample complexity; CLASSIFICATION;

D O I：

10.1080/03610920903140288

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

Bounds on the risk play a crucial role in statistical learning theory. They usually involve as capacity measure of the model studied the VC dimension or one of its extensions. In classification, such oVC dimensionso exist for models taking values in {0, 1}, [[1, Q]], and . We introduce the generalizations appropriate for the missing case, the one of models with values in Q. This provides us with a new guaranteed risk for M-SVMs. For those models, a sharper bound is obtained by using the Rademacher complexity.

引用

页码：543 / 557

页数：15

共 41 条

[1] Combining Multi-class SVMs with Linear Ensemble Methods that Estimate the Class Posterior Probabilities
Guermeur, Yann
COMMUNICATIONS IN STATISTICS-THEORY AND METHODS, 2013, 42 (16) : 3011 - 3030
[2] A pool of classifiers by SLP: A multi-class case
Raudys, Sarunas
Denisov, Vitalij
Bielskis, Antanas Andrius
IMAGE ANALYSIS AND RECOGNITION, PT 2, 2006, 4142 : 47 - 56
[3] Explaining deep multi-class time series classifiers
Doddaiah, Ramesh
Parvatharaju, Prathyush S.
Rundensteiner, Elke
Hartvigsen, Thomas
KNOWLEDGE AND INFORMATION SYSTEMS, 2024, 66 (06) : 3497 - 3521
[4] Robust Loss functions for Learning Multi-Class Classifiers
Kumar, Himanshu
Sastry, P. S.
2018 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2018, : 687 - 692
[5] Construction of Multi-class Classifiers by Extreme Learning Machine Based One-class Classifiers
Gautam, Chandan
Tiwari, Aruna
Ravindran, Sriram
2016 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2016, : 2001 - 2007
[6] A Study on Multi-Class Online Fuzzy Classifiers for Dynamic Environments
Ajimoto, Kensuke
Yamamoto, Yuma
Kusunoki, Yoshifumi
Nakashima, Tomoharu
2024 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS, FUZZ-IEEE 2024, 2024,
[7] Cascading SVMS as a tool for medical diagnosis using multi-class gene expression data
Flaounas, Ilias N.
Iakovidis, Dimitris K.
Maroulis, Dimitris E.
INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS, 2006, 15 (03) : 335 - 352
[8] Multi-class SVMs Analysis of Side-Channel Information of Elliptic Curve Cryptosystem
Saeedi, Ehsan
Hossain, Md. Selim
Kong, Yinan
PROCEEDINGS OF THE 2015 INTERNATIONAL SYMPOSIUM ON PERFORMANCE EVALUATION OF COMPUTER AND TELECOMMUNICATION SYSTEMS (SPECTS), 2015,
[9] MULTI-CLASS CLASSIFIERS BASED ON BINARY CLASSIFIERS: PERFORMANCE, EFFICIENCY, AND MINIMUM CODING MATRIX DISTANCES
Beekhof, Fokko
Voloshynovskiy, Sviatoslav
Koval, Oleksiy
Holotyak, Taras
2009 IEEE INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING, 2009, : 270 - +
[10] Interpretable Classifiers in Precision Medicine: Feature Selection and Multi-class Categorization
Schirra, Lyn-Rouven
Schmid, Florian
Kestler, Hans A.
Lausser, Ludwig
ARTIFICIAL NEURAL NETWORKS IN PATTERN RECOGNITION, 2016, 9896 : 105 - 116

← 1 2 3 4 5 →