ON EXPONENTIAL BOUNDS ON THE BAYES RISK OF THE KERNEL CLASSIFICATION RULE

被引：8

作者：

KRZYZAK, A

机构：

[1] Department of Computer Science, Concordia University, Montréal, H3G, 1M8

来源：

IEEE TRANSACTIONS ON INFORMATION THEORY | 1991年 / 37卷 / 03期

基金：

加拿大自然科学与工程研究理事会;

关键词：

KERNEL CLASSIFICATION RULE; L1 STRONG CONSISTENCY; RATES OF STRONG CONVERGENCE; EXPONENTIAL INEQUALITY;

D O I：

10.1109/18.79905

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Improved exponential bounds on Bayes probability of error for the nonparametric kernel classification rule are derived. It is shown, using the martingale device, that weak, strong, and complete L1 Bayes risk consistencies are equivalent. Consequently the conditions on the smoothing sequence h(n) --> 0 and nh(n) --> infinity are necessary and sufficient for Bayes rish consistency of the kernel classification rule. The rate of convergence of the kernel classification rule is also given.

引用

页码：490 / 499

页数：10

共 50 条

[41] BOUNDS ON THE BAYES AND MINIMAX RISK FOR SIGNAL PARAMETER-ESTIMATION
BROWN, LD
LIU, RC
IEEE TRANSACTIONS ON INFORMATION THEORY, 1993, 39 (04) : 1386 - 1394
[42] Error Bounds for Low-Rank Approximations of the First Exponential Integral Kernel
Nunes, A. L.
Vasconcelos, P. B.
Ahues, M.
NUMERICAL FUNCTIONAL ANALYSIS AND OPTIMIZATION, 2013, 34 (01) : 74 - 93
[43] Hierarchical Multilabel Classification with Minimum Bayes Risk
Bi, Wei
Kwok, James T.
12TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM 2012), 2012, : 101 - 110
[44] LOWER BOUND ON BAYES RISK IN CLASSIFICATION PROBLEMS
KIRMANI, SNUA
ANNALS OF THE INSTITUTE OF STATISTICAL MATHEMATICS, 1976, 28 (03) : 385 - 387
[45] Neural network directed Bayes decision rule for moving target classification
Azimi-Sadjadi, MR
Yu, X
AUTOMATIC TARGET RECOGNITION IX, 1999, 3718 : 152 - 163
[46] Neural network directed bayes decision rule for moving target classification
Yu, X
Azimi-Sadjadi, MR
IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 2000, 36 (01) : 176 - 188
[47] ASYMPTOTIC PROPERTIES OF PROBABILITY OF FALSE CLASSIFICATION IN CASE OF BAYES DECISION RULE
PODDUBNYI, GV
AUTOMATION AND REMOTE CONTROL, 1973, 34 (12) : 1894 - 1904
[48] Empirical Bayes decision rule for classification on defective items in Weibull distribution
Chang, Shui-Ching
Li, Tze Fen
APPLIED MATHEMATICS AND COMPUTATION, 2006, 182 (01) : 425 - 433
[49] NEW CLASS OF BOUNDS ON BAYES RISK IN MULTIHYPOTHESIS PATTERN-RECOGNITION
DEVIJVER, PA
IEEE TRANSACTIONS ON COMPUTERS, 1974, C 23 (01) : 70 - 80
[50] Excess Risk Bounds for the Bayes Risk using Variational Inference in Latent Gaussian Models
Sheth, Rishit
Khardon, Roni
ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30

← 1 2 3 4 5 →